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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional or traumatic events, specifically focusing on loss, suffering, or danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.70
    alnız
    -0.63
     Porn
    -0.62
    üyada
    -0.60
    ControllerAdvice
    -0.58
     EconPapers
    -0.57
    gebras
    -0.55
    Hochspringen
    -0.55
    EndInit
    -0.55
     pardon
    -0.54
    POSITIVE LOGITS
     فريبيس
    0.87
    !("{
    0.55
    ]})
    0.51
     للمعارف
    0.49
    <sup>
    0.48
    webElement
    0.48
    رشف
    0.48
    [][]
    0.48
    masını
    0.47
     Baus
    0.47
    Act Density 0.235%

    No Known Activations