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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal feelings or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelper
    -0.74
    certainly
    -0.62
     certainly
    -0.62
    ınd
    -0.60
     @}
    -0.59
    oges
    -0.58
     also
    -0.58
    SOUNDBITE
    -0.57
     zwar
    -0.56
     également
    -0.56
    POSITIVE LOGITS
     Просто
    0.91
     Simplemente
    0.81
    Просто
    0.80
     egyszerű
    0.77
     simply
    0.76
     незавершена
    0.74
     simplesmente
    0.72
    Simply
    0.71
     plain
    0.70
    simply
    0.69
    Act Density 0.241%

    No Known Activations