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

    Neuronpedia

    INDEX
    Explanations

    the possessive form of nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "s"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agos
    -0.70
    ey
    -0.63
    isch
    -0.62
    doms
    -0.59
    izzard
    -0.59
    esm
    -0.58
    trust
    -0.58
    cake
    -0.57
    Wars
    -0.56
     Archdemon
    -0.56
    POSITIVE LOGITS
     why
    0.92
     how
    0.89
     whats
    0.88
     another
    0.88
     what
    0.86
     excerpts
    0.80
    how
    0.78
    omething
    0.77
     recap
    0.76
     some
    0.75
    Act Density 0.022%

    No Known Activations