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

    Neuronpedia

    INDEX
    Explanations

    numbers

    oai_token-act-pair · gpt-3.5-turbo

    the specific character "Ĺ" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iddles
    -0.86
    asonic
    -0.79
    apping
    -0.79
    idges
    -0.77
    awar
    -0.76
    agin
    -0.73
     Beir
    -0.72
    ishers
    -0.71
    agonists
    -0.69
     ILCS
    -0.69
    POSITIVE LOGITS
    ï¸ı
    0.97
    é»Ĵ
    0.89
    æĸ¹
    0.86
    lishing
    0.82
    lihood
    0.79
    gers
    0.77
    lish
    0.75
    âĪ
    0.74
    DEN
    0.74
    åĪ
    0.73
    Act Density 0.026%

    No Known Activations