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

    Neuronpedia

    INDEX
    Explanations

    expressions of enjoyment and amusement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.81
     Normdatei
    -0.76
    IsMutable
    -0.74
    μβρίου
    -0.73
     scorso
    -0.73
    ;">
    -0.71
    자인
    -0.70
     Whittaker
    -0.70
    LabelTagHelper
    -0.69
    滓
    -0.68
    POSITIVE LOGITS
     fun
    1.55
     FUN
    1.55
    FUN
    1.39
     Fun
    1.37
    fun
    1.35
    Fun
    1.26
    funcs
    1.00
     Spaß
    0.97
     functools
    0.96
     functor
    0.94
    Act Density 0.022%

    No Known Activations