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

    Neuronpedia

    INDEX
    Explanations

    references to things or concepts being seen, mentioned, played, allowed, captured, killed, made, spent, done, featured, shared, experienced, dominated, awarded, or bought thus far

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progress or accomplishments so far

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĻ
    -0.66
    vation
    -0.62
    chio
    -0.62
    pron
    -0.60
     constants
    -0.59
     Cosponsors
    -0.58
    CLOSE
    -0.57
    inders
    -0.56
     Benefits
    -0.54
    Sys
    -0.54
    POSITIVE LOGITS
    ounding
    0.72
    ounds
    0.72
    ebin
    0.71
    interstitial
    0.66
    itiz
    0.65
     incarnation
    0.60
    due
    0.59
     gestation
    0.59
    .�
    0.58
     unsuccessful
    0.57
    Act Density 0.034%

    No Known Activations