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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific individual

    oai_token-act-pair · gpt-3.5-turbo

    references to Julian Assange and his involvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atility
    -0.74
    FU
    -0.73
    tml
    -0.72
    PATH
    -0.68
    relation
    -0.67
    uns
    -0.67
    atile
    -0.67
    olina
    -0.65
     Krug
    -0.64
     Solitaire
    -0.64
    POSITIVE LOGITS
     Assange
    1.09
    ovic
    0.95
    Leaks
    0.87
    ylum
    0.84
    ileaks
    0.79
    ovich
    0.77
    yer
    0.75
    minster
    0.73
    pad
    0.73
    quist
    0.72
    Act Density 0.018%

    No Known Activations