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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific dietary preference

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of "arian" ideologies or lifestyles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    err
    -0.76
    pless
    -0.71
    bsite
    -0.70
    leaf
    -0.70
    gur
    -0.67
    uring
    -0.66
    estation
    -0.66
    FFER
    -0.66
    urated
    -0.65
    ptions
    -0.64
    POSITIVE LOGITS
    ism
    0.99
    hip
    0.95
    arian
    0.84
    cies
    0.81
    amental
    0.80
     Kirin
    0.79
     laureate
    0.79
    naire
    0.77
    ity
    0.76
    arians
    0.74
    Act Density 0.043%

    No Known Activations