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

    Neuronpedia

    INDEX
    Explanations

    concepts related to filtering, selection, and adjustment processes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.95
     ExecuteAsync
    -0.94
    InvalidProtocol
    -0.91
    Personensuche
    -0.90
    LookAnd
    -0.84
    InputBorder
    -0.77
     فريبيس
    -0.76
     Cæsar
    -0.75
     EClass
    -0.73
     виправивши
    -0.73
    POSITIVE LOGITS
     makes
    0.84
     Makes
    0.74
    这让
    0.71
     thus
    0.69
    Makes
    0.69
     MAKES
    0.65
     gives
    0.60
     therefore
    0.60
     adds
    0.59
     helps
    0.58
    Act Density 0.685%

    No Known Activations