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

    Neuronpedia

    INDEX
    Explanations

    references to legal rules and procedures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ſelves
    -0.96
    CloseOperation
    -0.95
     Monfieur
    -0.95
    makeConstraints
    -0.92
     Majefty
    -0.92
     itſelf
    -0.91
     greateſt
    -0.91
     للاسماء
    -0.90
    lapsingToolbar
    -0.88
     myſelf
    -0.88
    POSITIVE LOGITS
     and
    0.45
     Se
    0.45
     W
    0.44
     which
    0.44
    tet
    0.44
     cánh
    0.43
     mix
    0.42
    ;
    0.42
    .
    0.41
     terre
    0.41
    Act Density 0.021%

    No Known Activations