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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of success or fulfillment

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to the concepts of vanity and futility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ider
    -0.66
    dule
    -0.65
    iew
    -0.62
    Inter
    -0.60
    GN
    -0.60
    ors
    -0.59
    ola
    -0.59
    hn
    -0.59
     overall
    -0.58
    hin
    -0.58
    POSITIVE LOGITS
     vain
    4.44
     futile
    2.29
     unsuccessfully
    1.75
     valiant
    1.45
     foolish
    1.30
     earnest
    1.26
     vanity
    1.20
     frantically
    1.19
     folly
    1.16
     desperately
    1.15
    Act Density 0.037%

    No Known Activations