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

    Neuronpedia

    INDEX
    Explanations

    adjectives indicating importance or necessity

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating importance or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arij
    -0.71
     vomit
    -0.69
     vom
    -0.69
    renheit
    -0.68
    flat
    -0.66
     sweats
    -0.64
    elf
    -0.61
    çİĭ
    -0.59
    uclear
    -0.59
    qus
    -0.58
    POSITIVE LOGITS
     determining
    0.79
     deterrent
    0.78
     adjunct
    0.78
     safeguard
    0.77
     because
    0.73
     motivating
    0.72
     for
    0.71
     distinguishing
    0.71
     integral
    0.70
     limiting
    0.70
    Act Density 0.102%

    No Known Activations