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

    Neuronpedia

    INDEX
    Explanations

    capital single letters followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'S' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CPR
    -0.69
     unrestricted
    -0.67
     crib
    -0.67
    tops
    -0.66
     Ribbon
    -0.62
     techno
    -0.61
     stressed
    -0.61
     undecided
    -0.61
     narc
    -0.61
     cord
    -0.60
    POSITIVE LOGITS
    ixty
    1.34
    ESSION
    1.33
    ierra
    1.26
    olutions
    1.24
    atisf
    1.24
    OUND
    1.23
    ometime
    1.23
    ustain
    1.20
    atellite
    1.20
    omew
    1.20
    Act Density 0.056%

    No Known Activations