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. 291
    Prev
    Next
    INDEX
    Explanations

    references to left-handedness

    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
     commerce
    -0.77
     blend
    -0.66
     gravity
    -0.64
     attraction
    -0.62
     Trident
    -0.61
     VID
    -0.61
     rides
    -0.61
     peace
    -0.61
     workspace
    -0.61
     purse
    -0.59
    POSITIVE LOGITS
    staff
    0.84
    central
    0.82
    amel
    0.81
    acerb
    0.81
    given
    0.80
    clair
    0.79
    shield
    0.78
    aways
    0.78
    handed
    0.78
    again
    0.77
    Activations Density 0.009%

    No Known Activations