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

    Neuronpedia

    INDEX
    Explanations

    names of historical figures

    oai_token-act-pair · gpt-3.5-turbo

    names of historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.86
    axy
    -0.81
    Safety
    -0.81
     actionGroup
    -0.80
    KY
    -0.80
    security
    -0.79
     dashboard
    -0.78
    Premium
    -0.76
    UFC
    -0.75
     cybersecurity
    -0.75
    POSITIVE LOGITS
     Augustus
    1.26
     Herbert
    1.16
     Napoleon
    1.16
     Francis
    1.15
     Edward
    1.10
     Ferdinand
    1.09
     Henry
    1.09
     Pope
    1.08
     Franks
    1.07
     Howe
    1.06
    Act Density 0.282%

    No Known Activations