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

    Neuronpedia

    INDEX
    Explanations

    expressions related to desires and preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    تقاوى
    -0.72
    +#+#
    -0.68
    matchCondition
    -0.67
    Hentet
    -0.52
     pleaſure
    -0.51
     lun
    -0.50
    richTextPanel
    -0.50
     мәкал
    -0.50
     cloche
    -0.50
    &__
    -0.49
    POSITIVE LOGITS
     crainte
    0.50
     Verlust
    0.50
    raszamy
    0.47
    avoid
    0.47
     nadzieję
    0.46
    Avoiding
    0.46
     visión
    0.45
     pozycji
    0.45
     prevención
    0.45
     Gefahr
    0.45
    Act Density 0.385%

    No Known Activations