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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating caution or exceptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional or uncertain outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eday
    -0.85
    timer
    -0.71
    fw
    -0.71
    aughs
    -0.71
    ults
    -0.70
    iry
    -0.69
    maybe
    -0.68
    esi
    -0.67
    sometimes
    -0.66
    perhaps
    -0.65
    POSITIVE LOGITS
     correlate
    0.86
     synonymous
    0.85
     equate
    0.83
     conducive
    0.82
     necessarily
    0.82
     indicative
    0.76
     anymore
    0.76
     translate
    0.75
    erest
    0.75
     correlated
    0.73
    Act Density 0.047%

    No Known Activations