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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical injuries or scars

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     utop
    -0.98
     robus
    -0.93
     siff
    -0.92
     solidar
    -0.89
     bascul
    -0.89
     incess
    -0.88
     meras
    -0.87
     parati
    -0.87
     geolog
    -0.85
     spion
    -0.84
    POSITIVE LOGITS
     scars
    0.71
     marks
    0.61
     inflicted
    0.60
     loopt
    0.58
     caused
    0.57
     szüks
    0.57
     visible
    0.54
     scarred
    0.53
     registrada
    0.52
     formed
    0.52
    Act Density 0.272%

    No Known Activations