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

    Neuronpedia

    INDEX
    Explanations

    names of people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bailed
    -0.63
     reign
    -0.60
     nights
    -0.60
     succeeding
    -0.60
     fingerprints
    -0.60
     optionally
    -0.56
     Alleg
    -0.56
     heels
    -0.55
     scalp
    -0.55
    odder
    -0.55
    POSITIVE LOGITS
    acan
    1.09
    é¾įå
    0.87
    olit
    0.86
    annis
    0.84
    acho
    0.84
    lda
    0.80
    aca
    0.80
    ACA
    0.78
    throp
    0.78
    heart
    0.78
    Act Density 0.068%

    No Known Activations