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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical pain and emotional distress

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional suffering and distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inaug
    -0.77
     prest
    -0.77
    ranch
    -0.72
     proficiency
    -0.71
    erential
    -0.71
     charism
    -0.71
    ospons
    -0.70
    tains
    -0.70
     favorably
    -0.70
    arthed
    -0.69
    POSITIVE LOGITS
     unbearable
    1.27
     crying
    1.18
     agony
    1.13
     anguish
    1.12
     tears
    1.12
     numb
    1.09
     hurts
    1.08
     misery
    1.05
    xiety
    1.04
     helpless
    1.03
    Act Density 0.835%

    No Known Activations