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

    Neuronpedia

    INDEX
    Explanations

    punctuations and symbols used for formatting or separating items in a list

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    logen
    -0.60
    -0.52
     hoarse
    -0.48
     anges
    -0.47
     Anon
    -0.47
     Ngb
    -0.47
    yargs
    -0.47
     onResponse
    -0.46
    kuuta
    -0.46
     Poseidon
    -0.45
    POSITIVE LOGITS
     defaultstate
    0.63
    corrência
    0.60
    giveness
    0.59
     StatelessWidget
    0.57
    phans
    0.57
    findpost
    0.57
    Controllo
    0.57
    Vidite
    0.56
    CreateModel
    0.56
    enterOuterAlt
    0.56
    Act Density 0.190%

    No Known Activations