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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a colon

    oai_token-act-pair · gpt-3.5-turbo

    references to authorship or creators of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Of
    -0.59
    pei
    -0.59
    76561
    -0.55
    SourceFile
    -0.55
    ocene
    -0.55
    =-=-
    -0.54
    of
    -0.54
    ghai
    -0.54
    ornia
    -0.53
    etheless
    -0.53
    POSITIVE LOGITS
     redes
    0.54
     vain
    0.46
     correcting
    0.45
     chance
    0.45
     encountering
    0.43
     misfortune
    0.43
     mistake
    0.43
     improving
    0.42
     educating
    0.42
     glory
    0.42
    Act Density 1.276%

    No Known Activations