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

    Neuronpedia

    INDEX
    Explanations

    topics related to influences on speech and community decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingle
    -0.19
    ãĥ¼ãĥĢ
    -0.15
    alone
    -0.14
    åĺĽ
    -0.14
    ardon
    -0.14
     UNUSED
    -0.14
    алеж
    -0.14
    اÛĮÙĩ
    -0.14
    Aliases
    -0.14
    _marshall
    -0.14
    POSITIVE LOGITS
     but
    0.21
     will
    0.19
     also
    0.18
     during
    0.18
     actually
    0.18
     has
    0.18
     may
    0.17
     via
    0.17
     is
    0.17
     suddenly
    0.17
    Act Density 0.488%

    No Known Activations