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

    Neuronpedia

    INDEX
    Explanations

    the word or word segment "oles"

    oai_token-act-pair · gpt-4-turbo

    words related to holes or cavities

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of a particular name or term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reply
    -0.68
    è¦ļéĨĴ
    -0.65
    Flight
    -0.65
    ãģ®å®
    -0.63
    ANC
    -0.62
    EXP
    -0.61
     Chronicle
    -0.61
    ãĥ©ãĥ³
    -0.59
     Judgment
    -0.58
     EDITION
    -0.57
    POSITIVE LOGITS
    oles
    1.43
    ole
    0.99
    pora
    0.94
    ols
    0.92
    terness
    0.89
    ummer
    0.87
    hift
    0.87
    hene
    0.86
    ophy
    0.84
    ippi
    0.83
    Act Density 0.003%

    No Known Activations