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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    instances of the token 'Col', indicating a reference to institutions or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Werewolf
    -0.74
    ARK
    -0.62
    DragonMagazine
    -0.61
     forth
    -0.61
    cffffcc
    -0.58
     Danish
    -0.56
     Icelandic
    -0.56
     DARK
    -0.54
     Helsinki
    -0.53
    IELD
    -0.53
    POSITIVE LOGITS
    ossal
    1.31
    onel
    1.29
    onial
    1.16
    leen
    1.16
    ophon
    1.14
    ombo
    1.13
    ossus
    1.09
    umbo
    1.08
    oured
    1.07
    ored
    1.03
    Act Density 0.031%

    No Known Activations