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

    Neuronpedia

    INDEX
    Explanations

    words related to positive assessments or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quæ
    -1.01
     Houſe
    -0.96
     houſe
    -0.96
     piú
    -0.93
     fevere
    -0.89
     ſever
    -0.88
    seamnă
    -0.87
     feroit
    -0.86
     raiſ
    -0.86
     leaſt
    -0.84
    POSITIVE LOGITS
     виправивши
    0.73
    ftagPool
    0.57
    UrlResolution
    0.57
    amodel
    0.57
    Demografie
    0.54
    GEBURTSDATUM
    0.54
    Datuak
    0.53
    imensional
    0.53
     Reverso
    0.52
    зулта
    0.52
    Act Density 0.152%

    No Known Activations