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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to comparisons or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    references to philosophical concepts or ideas related to existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.66
    Meanwhile
    -0.58
     enthusi
    -0.58
     Seym
    -0.54
     Vaugh
    -0.54
    aunted
    -0.54
    Hundreds
    -0.54
    PDATE
    -0.53
    oppable
    -0.53
    kefeller
    -0.52
    POSITIVE LOGITS
     noun
    1.14
    )?
    0.91
     pronouns
    0.90
     abbre
    0.89
     verb
    0.87
     verbs
    0.86
     pronoun
    0.86
     adjective
    0.85
     adject
    0.81
     plur
    0.77
    Act Density 0.963%

    No Known Activations