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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating fulfillment or meeting expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    up to expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    htbp
    -0.45
     wilfully
    -0.45
     []:
    -0.43
    angerie
    -0.43
    例句
    -0.42
    #
    -0.41
    抽
    -0.39
    orgs
    -0.39
    üyada
    -0.38
    yarnpkg
    -0.38
    POSITIVE LOGITS
    VersionUID
    0.53
     fulfill
    0.53
     reputa
    0.51
    PreExecute
    0.50
     speł
    0.48
     rendement
    0.48
    tagHelperRunner
    0.48
     voldo
    0.47
     cumple
    0.47
    ỏa
    0.46
    Act Density 0.003%

    No Known Activations