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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence or consideration of certain conditions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.86
    TestingModule
    -0.81
    DoubleQuotes
    -0.81
    ArgsConstructor
    -0.71
     estekak
    -0.70
     Roskov
    -0.70
     насељу
    -0.69
    Autoritní
    -0.69
    OrBuilder
    -0.68
    Personensuche
    -0.68
    POSITIVE LOGITS
     personer
    0.50
     “
    0.48
     ogóle
    0.47
    Биография
    0.47
     яко
    0.43
     «
    0.42
     Bezirk
    0.42
    fe
    0.42
    ở
    0.42
    vač
    0.42
    Act Density 0.867%

    No Known Activations