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

    Neuronpedia

    INDEX
    Explanations

    expressions related to community engagement and social responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.30
    /her
    -0.20
    /or
    -0.20
    /out
    -0.18
    /on
    -0.18
    /of
    -0.18
    /to
    -0.17
    /by
    -0.15
    /the
    -0.15
    /how
    -0.15
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.22
    /report
    0.20
    ulate
    0.17
    ä¼ij
    0.14
    entially
    0.14
    ible
    0.14
    ÏĬκ
    0.14
    /format
    0.14
    atively
    0.14
    /signup
    0.14
    Act Density 1.962%

    No Known Activations