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

    Neuronpedia

    INDEX
    Explanations

    words related to military operations or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with geopolitical boundaries and conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mathemat
    -0.78
     contrace
    -0.67
    bies
    -0.67
    baugh
    -0.66
    umenthal
    -0.66
     reconc
    -0.66
    quished
    -0.64
    ingers
    -0.64
     aspir
    -0.64
     loopholes
    -0.63
    POSITIVE LOGITS
    ï¸ı
    1.15
    ÏĦ
    1.09
    ¸
    1.01
    ³
    0.97
    ½
    0.95
    ¾
    0.95
    ε
    0.94
    ĥ
    0.92
    °
    0.92
    ł
    0.92
    Act Density 0.018%

    No Known Activations