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

    Neuronpedia

    INDEX
    Explanations

    specific medical or scientific terminology related to health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -
    -0.86
    ,
    -0.78
    (
    -0.77
    f
    -0.72
     in
    -0.72
    v
    -0.69
    .
    -0.69
     (
    -0.68
    r
    -0.67
    b
    -0.67
    POSITIVE LOGITS
     autorytatywna
    1.88
     beginnetje
    1.82
     itſelf
    1.80
     myſelf
    1.78
    OGND
    1.77
    GEBURTSDATUM
    1.77
     Roskov
    1.76
     виправивши
    1.71
     незавершена
    1.71
    ſelf
    1.69
    Act Density 0.714%

    No Known Activations