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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal and official proceedings

    oai_token-act-pair · gpt-3.5-turbo

    indicators of significant events or actions within a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     unlucky
    -0.80
     agon
    -0.75
     estranged
    -0.74
     romance
    -0.69
    tics
    -0.69
     centrally
    -0.68
     inactive
    -0.68
     habit
    -0.67
     discarded
    -0.67
     endeavour
    -0.67
    POSITIVE LOGITS
    Narr
    1.01
    Howard
    0.99
    Senator
    0.98
    AUD
    0.97
    Interview
    0.96
    BILL
    0.95
    Dick
    0.95
    JOHN
    0.94
    Anyway
    0.93
    Question
    0.92
    Act Density 0.303%

    No Known Activations