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

    Neuronpedia

    INDEX
    Explanations

    instances of events or items related to being the first in a series or the beginning of something

    oai_token-act-pair · gpt-3.5-turbo

    references to inaugural events and significant first occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bane
    -0.80
    rage
    -0.77
    aceutical
    -0.75
    morph
    -0.75
    chrom
    -0.74
    omedical
    -0.71
    angs
    -0.67
    esty
    -0.67
    nery
    -0.66
    riter
    -0.66
    POSITIVE LOGITS
     edition
    0.89
     inaugural
    0.88
     Pengu
    0.88
     kickoff
    0.85
     season
    0.85
     foray
    0.81
     anniversary
    0.81
    antha
    0.81
     festivities
    0.81
    ãĥ¼ãĥĨãĤ£
    0.78
    Act Density 0.010%

    No Known Activations