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

    Neuronpedia

    INDEX
    Explanations

    phrases and questions related to identity and self-reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ึ
    -0.13
    ãģĭãģij
    -0.12
    acios
    -0.12
    obra
    -0.11
    .CopyTo
    -0.11
    /epl
    -0.11
    klä
    -0.11
    ãĤ¯ãĤ»
    -0.11
    ersonic
    -0.11
    YTE
    -0.11
    POSITIVE LOGITS
     Am
    1.22
     am
    1.20
    Am
    1.09
    -Am
    0.97
    _am
    0.94
    -am
    0.93
    .am
    0.91
     amplitude
    0.87
     AM
    0.86
    (am
    0.86
    Act Density 0.400%

    No Known Activations