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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "pale" or related terms in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "pale" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©Ł
    -0.64
    sers
    -0.63
    ually
    -0.62
     loudly
    -0.62
     jammed
    -0.61
    ELS
    -0.61
     reel
    -0.60
     ACTIONS
    -0.59
    ÄŁ
    -0.58
     jams
    -0.57
    POSITIVE LOGITS
    olithic
    1.54
    ozo
    1.16
    ogen
    1.13
    ohyd
    1.12
    ogene
    1.07
    opath
    1.04
    ont
    1.03
    ocl
    1.00
    ocene
    0.97
    croft
    0.96
    Act Density 0.047%

    No Known Activations