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

    Neuronpedia

    INDEX
    Explanations

    situations involving physical vulnerability or injury, particularly in violent contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endif
    -0.52
     cie
    -0.45
    gmd
    -0.45
     
    -0.44
     leads
    -0.44
     poivre
    -0.43
     lead
    -0.43
     напря
    -0.42
     cul
    -0.42
    Heading
    -0.41
    POSITIVE LOGITS
     reclining
    0.99
     beginnetje
    0.94
     تضيفلها
    0.91
    Rüyada
    0.89
     kneeling
    0.87
     reclin
    0.87
     prostrate
    0.86
    ContentAsync
    0.85
    IndentedString
    0.84
     couch
    0.83
    Act Density 0.227%

    No Known Activations