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

    Neuronpedia

    INDEX
    Explanations

    phrases related to configuration or settings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "conf" indicating a relation to confidence or confirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shovel
    -0.75
     Gram
    -0.72
     jug
    -0.69
     Lawn
    -0.68
     equivalent
    -0.67
     mill
    -0.67
     retail
    -0.64
     tub
    -0.63
     adjunct
    -0.63
     staple
    -0.62
    POSITIVE LOGITS
    conf
    4.04
    Conf
    2.25
     Conf
    1.68
    conference
    1.34
     conf
    1.31
    confirmed
    1.29
    confidence
    1.25
    config
    1.16
    conv
    1.09
    cfg
    1.08
    Act Density 0.015%

    No Known Activations