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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal preferences and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afficheront
    -0.69
    UnsafeEnabled
    -0.68
     NSCoder
    -0.61
    audiovisuel
    -0.59
    awtextra
    -0.54
    phed
    -0.54
     Réponses
    -0.53
     createState
    -0.53
    AddTagHelper
    -0.53
    tagext
    -0.53
    POSITIVE LOGITS
     usually
    0.70
     suele
    0.70
     costuma
    0.69
     brukar
    0.69
     бывает
    0.66
    BeginContext
    0.66
     suelen
    0.65
     always
    0.64
    Usually
    0.61
    always
    0.61
    Act Density 0.654%

    No Known Activations