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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals or figures in storytelling or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     issu
    -0.64
     DISTRICT
    -0.64
     RELE
    -0.63
    LED
    -0.61
    unker
    -0.59
     FINAL
    -0.57
     disapp
    -0.57
     Saiyan
    -0.56
    enter
    -0.55
     Locations
    -0.55
    POSITIVE LOGITS
     him
    0.94
     whom
    0.93
    him
    0.81
     teammate
    0.80
     classmate
    0.78
     hers
    0.75
    his
    0.72
     affection
    0.71
    aus
    0.67
     Jr
    0.67
    Act Density 1.175%

    No Known Activations