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

    Neuronpedia

    INDEX
    Explanations

    legal case references and citations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.84
    MigrationBuilder
    -0.72
     shadow
    -0.58
     ha
    -0.53
    gms
    -0.53
    mitos
    -0.52
     Fle
    -0.52
     mxArray
    -0.52
    kons
    -0.51
     han
    -0.51
    POSITIVE LOGITS
    harusnya
    0.58
    Espèce
    0.56
     Ababa
    0.56
     محفوظة
    0.52
     ſeveral
    0.52
    wiſe
    0.52
    roidered
    0.51
    ſelf
    0.51
     virke
    0.50
     Италијани
    0.49
    Act Density 0.004%

    No Known Activations