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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the beginning of events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aviv
    -0.17
    .***.***
    -0.15
    alara
    -0.15
    alion
    -0.15
    份
    -0.14
    Ñijл
    -0.14
    ulg
    -0.14
    lags
    -0.14
    éĺ¶
    -0.14
    alie
    -0.13
    POSITIVE LOGITS
    ainter
    0.16
    anco
    0.16
    æĸ
    0.15
     Observer
    0.15
    eh
    0.15
    890
    0.14
    cion
    0.14
    659
    0.14
    796
    0.14
    osen
    0.14
    Act Density 0.033%

    No Known Activations