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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating positivity and appreciation for experiences or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YPES
    -0.14
     ÐĴики
    -0.14
     Fucking
    -0.14
    plx
    -0.13
    ingleton
    -0.13
    416
    -0.13
     Wich
    -0.13
     mmc
    -0.13
    fuck
    -0.13
     Fuck
    -0.13
    POSITIVE LOGITS
    ç«ľ
    0.16
    erland
    0.16
    yield
    0.15
    iol
    0.15
    PCP
    0.14
     dust
    0.14
    quil
    0.14
     birth
    0.14
    erva
    0.14
    ÑĢÑĸд
    0.14
    Act Density 0.030%

    No Known Activations