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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 669
    Prev
    Next
    INDEX
    Explanations

    phrases that present alternative options or comparisons

    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
    nect
    -0.74
    IDA
    -0.74
    ryn
    -0.72
    tal
    -0.68
    acus
    -0.66
    uesday
    -0.66
    izons
    -0.64
    perse
    -0.64
    aunder
    -0.63
    overe
    -0.62
    POSITIVE LOGITS
     both
    0.73
     Schne
    0.70
    inctions
    0.65
    inction
    0.61
    iami
    0.60
    versely
    0.57
    ombat
    0.56
     imposing
    0.56
     literally
    0.56
    yg
    0.55
    Activations Density 0.110%

    No Known Activations