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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal cases

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference specific cases or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pec
    -0.75
    sis
    -0.74
    nea
    -0.70
    tsy
    -0.68
    ocracy
    -0.68
    flags
    -0.67
    oulder
    -0.66
    bra
    -0.66
    bench
    -0.65
    bn
    -0.64
    POSITIVE LOGITS
     conduc
    0.77
     paran
    0.69
     unsu
    0.68
     rods
    0.66
    icates
    0.64
    oran
    0.64
     Colony
    0.63
    tons
    0.63
     pitches
    0.61
     spheres
    0.61
    Act Density 0.044%

    No Known Activations