Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 315
    Prev
    Next
    INDEX
    Explanations

    references to location and distance

    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
    iman
    -0.76
    ction
    -0.64
    append
    -0.61
    ctl
    -0.61
    angered
    -0.61
    phrine
    -0.61
    amen
    -0.59
    igible
    -0.59
     hydra
    -0.58
    imon
    -0.58
    POSITIVE LOGITS
     kilometres
    0.79
     yards
    0.72
    near
    0.71
    square
    0.71
    itone
    0.71
    emale
    0.69
    far
    0.69
     uphill
    0.69
     metres
    0.69
     mile
    0.68
    Activations Density 1.190%

    No Known Activations