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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with thoughts and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    رشف
    -0.56
    chmal
    -0.55
     Stück
    -0.52
    fino
    -0.51
    /*
    -0.50
     Kalt
    -0.50
     piede
    -0.50
     epochs
    -0.50
    arası
    -0.49
    nessed
    -0.48
    POSITIVE LOGITS
     invokevirtual
    0.79
     instinctively
    0.77
     instinct
    0.77
     immediately
    0.77
     instin
    0.73
     intuiti
    0.70
     instantly
    0.67
     reflex
    0.67
     inmediatamente
    0.67
     reaction
    0.66
    Act Density 0.195%

    No Known Activations