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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or thanks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.69
    modelBuilder
    -0.65
    Rüyada
    -0.63
     defaultstate
    -0.60
    Дереккөздер
    -0.59
    出版年
    -0.57
     архивлан
    -0.56
    MethodManager
    -0.55
     externi
    -0.55
     _$
    -0.55
    POSITIVE LOGITS
     scholarship
    0.65
     thank
    0.60
    Danke
    0.57
     selamat
    0.56
    twimg
    0.55
     thanking
    0.55
    Thanks
    0.54
    thanks
    0.54
     thanked
    0.53
     thanks
    0.53
    Act Density 0.070%

    No Known Activations