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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals and specific actions related to personal interactions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.56
     resourceCulture
    -0.52
    лаг
    -0.47
    ckle
    -0.44
    <?
    -0.44
    anum
    -0.44
    évaluateur
    -0.43
    ัด
    -0.42
     Alto
    -0.41
    laşı
    -0.41
    POSITIVE LOGITS
     jealous
    0.85
     intervening
    0.80
     ikut
    0.79
     turut
    0.78
     envious
    0.77
    ampingi
    0.77
     accompanies
    0.75
     ebenfalls
    0.73
     concur
    0.73
     accompany
    0.72
    Act Density 0.318%

    No Known Activations