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

    Neuronpedia

    INDEX
    Explanations

    sentences that begin with "To" indicating intentions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ་་
    -0.73
    "}")
    -0.72
    fisher
    -0.68
     Efq
    -0.67
     initWithFrame
    -0.67
     NDEBUG
    -0.67
    endpush
    -0.66
    jetbrains
    -0.65
    yssey
    -0.65
     Ander
    -0.65
    POSITIVE LOGITS
    To
    2.47
     To
    2.45
     TO
    1.58
     to
    1.42
     Чтобы
    1.18
    Чтобы
    1.14
    setTo
    1.13
    DataTo
    1.12
     Toh
    1.06
    For
    1.01
    Act Density 0.049%

    No Known Activations