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

    Neuronpedia

    INDEX
    Explanations

    words starting with "ance"

    oai_token-act-pair · gpt-3.5-turbo

    words that denote states or conditions, particularly those involving the concept of balance or harmony

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amar
    -0.82
    ingen
    -0.78
    ocular
    -0.77
    onut
    -0.77
    iday
    -0.77
    rador
    -0.69
    ocon
    -0.69
    IFIC
    -0.69
     forget
    -0.68
    obos
    -0.66
    POSITIVE LOGITS
    llor
    0.94
    ments
    0.88
    ment
    0.85
    bringer
    0.84
    utics
    0.78
    utical
    0.75
    xual
    0.73
     fulfillment
    0.71
    etus
    0.70
    ll
    0.69
    Act Density 0.033%

    No Known Activations