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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals who are in leading positions or roles

    oai_token-act-pair · gpt-3.5-turbo

    leadership roles or positions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WATCHED
    -0.74
    ALLY
    -0.71
     Leone
    -0.65
    BLIC
    -0.63
    pload
    -0.59
    ascade
    -0.59
     Tsukuyomi
    -0.58
     mercy
    -0.58
    eatures
    -0.58
     constitu
    -0.57
    POSITIVE LOGITS
    ership
    1.26
    better
    1.01
    erer
    0.84
     singer
    0.83
    gers
    0.80
    boards
    0.80
    wig
    0.79
     negotiator
    0.77
    hun
    0.75
    bats
    0.73
    Act Density 0.037%

    No Known Activations