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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing disagreement or disillusionment

    oai_token-act-pair · gpt-3.5-turbo

    statements that highlight negation or contradiction regarding expectations or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     redes
    -0.78
    çīĪ
    -0.69
     ACTIONS
    -0.66
    asionally
    -0.63
     periodically
    -0.62
    YES
    -0.61
    姫
    -0.61
     margins
    -0.61
     unsus
    -0.60
    )))
    -0.59
    POSITIVE LOGITS
     anymore
    1.72
     nor
    1.34
    yet
    1.09
     necessarily
    0.98
     slightest
    0.90
     anybody
    0.85
     anywhere
    0.83
     yet
    0.81
    necess
    0.78
     any
    0.78
    Act Density 0.316%

    No Known Activations