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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "first"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something is the first occurrence of an event or situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maps
    -0.74
    morph
    -0.70
    appiness
    -0.63
    obby
    -0.63
    each
    -0.63
     Morty
    -0.62
    Ïī
    -0.62
    Downloadha
    -0.62
    ractor
    -0.59
    md
    -0.59
    POSITIVE LOGITS
     casualty
    0.97
     installment
    0.94
    born
    0.94
     baseman
    0.92
     foray
    0.91
     responders
    0.88
     thing
    0.85
     hurdle
    0.82
     indication
    0.82
     ever
    0.81
    Act Density 0.070%

    No Known Activations