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

    Neuronpedia

    INDEX
    Explanations

    concepts related to irreversible changes or finality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    psack
    -0.55
    calaureate
    -0.54
    出版年
    -0.52
     يتيمه
    -0.49
    Yet
    -0.47
     Told
    -0.46
    AttributeSet
    -0.46
     Yet
    -0.45
     lạ
    -0.43
    شرين
    -0.43
    POSITIVE LOGITS
     irrevocable
    0.84
     irreversible
    0.73
    Autoritní
    0.71
    vocable
    0.65
     irrever
    0.63
     оригіналу
    0.58
     once
    0.58
    boca
    0.57
     //$
    0.57
    ässä
    0.56
    Act Density 0.181%

    No Known Activations