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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the "<bos>" token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.68
    protoimpl
    -0.64
    новништво
    -0.64
    uxxxx
    -0.60
    UserScript
    -0.60
    CloseOperation
    -0.57
    DeleteBehavior
    -0.55
    曖昧さ回避
    -0.54
    onViewCreated
    -0.54
     Autorizaciones
    -0.52
    POSITIVE LOGITS
     Rouse
    0.41
    ngths
    0.40
     present
    0.39
    .*")]
    0.39
    RTGC
    0.38
     malam
    0.37
    mando
    0.36
    стоин
    0.36
    alga
    0.35
     Besten
    0.35
    Act Density 0.344%

    No Known Activations