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

    Neuronpedia

    INDEX
    Explanations

    words related to specific individual names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancies
    -0.71
    ancy
    -0.70
    IFF
    -0.69
    UA
    -0.69
     diapers
    -0.67
    rees
    -0.67
    arge
    -0.67
    ees
    -0.65
     Instruments
    -0.65
    ibr
    -0.64
    POSITIVE LOGITS
    unci
    0.92
    stadt
    0.86
    hoe
    0.84
    thro
    0.79
    terness
    0.79
    ahime
    0.73
    ovic
    0.72
    jection
    0.69
    worm
    0.69
    cephal
    0.69
    Act Density 0.058%

    No Known Activations