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

    Neuronpedia

    INDEX
    Explanations

    expressions and contexts related to fun and enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ;">
    -0.75
    AndEndTag
    -0.72
    μβρίου
    -0.71
    ztály
    -0.70
     rowspan
    -0.70
     ویکی‌آمباردا
    -0.69
     vectorielle
    -0.69
     CGA
    -0.69
     Ooster
    -0.69
     Normdatei
    -0.68
    POSITIVE LOGITS
     FUN
    1.21
     fun
    1.13
     Fun
    1.07
    fun
    1.07
    FUN
    1.06
    Fun
    0.97
    funcs
    0.89
     functools
    0.73
    nels
    0.69
     guys
    0.67
    Act Density 0.019%

    No Known Activations