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

    Neuronpedia

    INDEX
    Explanations

    the beginning of text or new sections in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saites
    -0.61
    RetentionPolicy
    -0.58
    ագրություններ
    -0.57
     فريبيس
    -0.56
     domesticated
    -0.53
    posób
    -0.51
    kine
    -0.50
    oxin
    -0.50
    Iden
    -0.49
     étudiant
    -0.48
    POSITIVE LOGITS
     abc
    1.57
    abc
    1.13
     AppCompatTheme
    1.08
     TextAppearance
    1.07
    WireFormatLite
    1.02
     مرئيه
    1.02
    ABC
    1.01
    expandindo
    1.00
     ABC
    0.99
    SuppressMessage
    0.88
    Act Density 0.017%

    No Known Activations