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

    Neuronpedia

    INDEX
    Explanations

    negations and certain forms of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ροι
    -0.61
    這位
    -0.59
     Cullen
    -0.57
    ary
    -0.57
    εις
    -0.56
    verständlich
    -0.54
     sosten
    -0.53
     sì
    -0.53
    iller
    -0.52
    iger
    -0.51
    POSITIVE LOGITS
    Geplaatst
    0.94
     ExecuteAsync
    0.87
    #
    0.84
    Portale
    0.81
    tikum
    0.76
    WaitGroup
    0.73
     სა
    0.72
    ensation
    0.72
    atism
    0.72
    ::_('
    0.71
    Act Density 0.070%

    No Known Activations