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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate evaluation or appreciation of work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    '.
    -0.49
     where
    -0.48
    visející
    -0.44
    Gweler
    -0.44
    Portail
    -0.41
    BITDA
    -0.41
     jendela
    -0.41
    !='
    -0.40
     plastiques
    -0.40
     endfor
    -0.40
    POSITIVE LOGITS
     désolés
    0.75
     ujednoznacz
    0.72
    pegno
    0.69
     Egli
    0.65
     Meksiku
    0.65
     BoxFit
    0.63
     ExecuteAsync
    0.63
     doubtnut
    0.61
    pewa
    0.60
     Оно
    0.59
    Act Density 0.252%

    No Known Activations