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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the beginning or start of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a beginning or start of an event or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sleep
    -0.75
    lean
    -0.73
    alty
    -0.60
    ult
    -0.60
    elo
    -0.59
    acha
    -0.59
    iesta
    -0.59
    iqueness
    -0.57
    ractor
    -0.57
    asha
    -0.56
    POSITIVE LOGITS
    -->
    0.77
     scratched
    0.70
    etts
    0.69
     scratching
    0.68
     examples
    0.66
     sympt
    0.66
    ++++++++++++++++
    0.66
    APTER
    0.64
     facet
    0.64
    %"
    0.63
    Act Density 0.118%

    No Known Activations