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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "To", indicating an intention or goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "}")
    -0.97
    UserScript
    -0.92
    ChildScrollView
    -0.83
     Superhosts
    -0.79
    ')")
    -0.77
    })`
    -0.74
    ⓧ
    -0.74
    %");
    -0.73
    цездатний
    -0.72
    WebElementEntity
    -0.72
    POSITIVE LOGITS
    To
    3.11
     To
    2.98
     TO
    1.79
    TO
    1.61
    setTo
    1.34
    For
    1.30
    to
    1.27
     Чтобы
    1.23
     Toh
    1.18
     For
    1.14
    Act Density 0.062%

    No Known Activations