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

    Neuronpedia

    INDEX
    Explanations

    objects, items, or things mentioned in a list

    oai_token-act-pair · gpt-3.5-turbo

    references to personal belongings and property-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kefeller
    -0.60
    rolet
    -0.57
    UTC
    -0.56
    inguished
    -0.54
    çīĪ
    -0.54
    payers
    -0.54
    etheless
    -0.54
    according
    -0.54
     Edited
    -0.53
    ajor
    -0.53
    POSITIVE LOGITS
     or
    1.40
     etc
    0.86
     OR
    0.80
     Or
    0.77
     unexpectedly
    0.72
     nor
    0.71
    ,
    0.68
    Or
    0.66
    /,
    0.65
    ®,
    0.65
    Act Density 0.780%

    No Known Activations