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

    Neuronpedia

    INDEX
    Explanations

    names of notable individuals or historical figures

    oai_token-act-pair · gpt-3.5-turbo

    names of notable historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fecture
    -0.85
    ierrez
    -0.82
    scenes
    -0.80
    */(
    -0.75
    EStreamFrame
    -0.74
     servicing
    -0.74
    merce
    -0.73
    bably
    -0.72
    ngth
    -0.71
    jriwal
    -0.71
    POSITIVE LOGITS
     Freud
    1.15
     Wilhelm
    1.09
     Lewis
    1.09
     von
    1.09
     Friedrich
    1.08
     Herbert
    1.08
     Herman
    1.08
     Marx
    1.08
     Edward
    1.07
     Greenberg
    1.06
    Act Density 0.297%

    No Known Activations