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

    Neuronpedia

    INDEX
    Explanations

    news sources

    oai_token-act-pair · gpt-3.5-turbo

    references to the news agency Reuters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gone
    -0.71
    gran
    -0.71
    ysis
    -0.71
    stood
    -0.61
    vil
    -0.60
     successors
    -0.60
    inent
    -0.60
    quer
    -0.60
     disenfranch
    -0.59
    chest
    -0.58
    POSITIVE LOGITS
    Reuters
    1.00
    PLIED
    1.00
    agascar
    0.86
    externalActionCode
    0.83
     Images
    0.78
    insula
    0.78
    AFP
    0.76
    CLASSIFIED
    0.76
     Seym
    0.75
    abwe
    0.75
    Act Density 0.009%

    No Known Activations