© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1435
    Prev
    Next
    INDEX
    Explanations

    the letter "V" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respecting
    -0.81
    respect
    -0.63
     containing
    -0.60
     consisting
    -0.58
    hent
    -0.58
    semble
    -0.56
     knockout
    -0.56
     lacking
    -0.56
     relying
    -0.56
     simplify
    -0.55
    POSITIVE LOGITS
    antage
    0.89
    hower
    0.88
    ItemThumbnailImage
    0.70
    verson
    0.70
    icious
    0.68
    iability
    0.68
    aye
    0.68
    Rush
    0.66
    indal
    0.66
    igious
    0.65
    Activations Density 0.014%

    No Known Activations