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

    Neuronpedia

    INDEX
    Explanations

    words related to specific languages

    oai_token-act-pair · gpt-3.5-turbo

    references to the Hebrew language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.92
    enegger
    -0.86
    awaru
    -0.81
    llan
    -0.78
    cling
    -0.75
    uristic
    -0.75
    emonium
    -0.74
    mble
    -0.73
    olicy
    -0.73
    ideshow
    -0.72
    POSITIVE LOGITS
     Hebrew
    1.03
    wings
    0.84
    hovah
    0.81
     labou
    0.81
     ×
    0.80
    soever
    0.75
    s
    0.75
     Torah
    0.72
     Canaan
    0.72
    ת
    0.72
    Act Density 0.002%

    No Known Activations