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

    Neuronpedia

    INDEX
    Explanations

    the word "s" at the end of words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the contraction "it's."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rebell
    -0.60
     Brune
    -0.58
    ertodd
    -0.57
    iling
    -0.57
     Guant
    -0.56
     Bagg
    -0.55
     Prior
    -0.55
    ipl
    -0.55
    igraph
    -0.54
     Continental
    -0.54
    POSITIVE LOGITS
     raining
    1.00
     impossible
    0.93
     imperative
    0.90
     advisable
    0.89
     unclear
    0.89
     worth
    0.86
     easier
    0.85
     easiest
    0.84
     doubtful
    0.82
     gonna
    0.82
    Act Density 0.112%

    No Known Activations