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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the start or conclusion of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leen
    -0.16
    at
    -0.15
    ese
    -0.15
     kr
    -0.14
     Dawn
    -0.14
    UPS
    -0.14
    icens
    -0.14
    IEL
    -0.14
    CASE
    -0.14
    rub
    -0.14
    POSITIVE LOGITS
    /end
    0.25
     of
    0.23
     end
    0.20
     stages
    0.19
    -end
    0.16
    Boss
    0.16
    /start
    0.16
     Of
    0.16
    vey
    0.15
     Boss
    0.15
    Act Density 0.033%

    No Known Activations