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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and attitudes related to opinions or experiences of individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of feelings or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anmar
    -0.65
    tainment
    -0.62
    uscript
    -0.57
     Binary
    -0.57
     Prospect
    -0.57
    ullivan
    -0.57
    opsis
    -0.57
    oret
    -0.56
     Puzzles
    -0.56
     varieties
    -0.55
    POSITIVE LOGITS
     obligated
    1.02
     compelled
    1.01
     betrayed
    0.98
     kins
    0.97
     acutely
    0.92
     obligation
    0.85
     obliged
    0.85
     pressure
    0.85
     violated
    0.82
     urgency
    0.81
    Act Density 0.161%

    No Known Activations