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

    Neuronpedia

    INDEX
    Explanations

    references to the term "guerilla" (or its variations) in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to guerrillas or guerrilla warfare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.84
    baugh
    -0.75
     Mour
    -0.73
    ropolitan
    -0.72
    heid
    -0.69
     Sacrament
    -0.67
    enment
    -0.67
     Cosponsors
    -0.65
     Cycle
    -0.64
    WARE
    -0.63
    POSITIVE LOGITS
     gu
    1.09
    inea
    1.02
    arant
    0.93
    vernment
    0.90
    ilts
    0.87
    ilt
    0.84
    arding
    0.83
    pload
    0.82
    isu
    0.80
    izoph
    0.79
    Act Density 0.003%

    No Known Activations