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

    Neuronpedia

    INDEX
    Explanations

    phrases related to licensing and distribution terms in software documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AUS
    -0.60
    AUT
    -0.56
    AUG
    -0.55
    AUDIO
    -0.55
    AUD
    -0.54
    EUR
    -0.54
     AUS
    -0.54
    AUR
    -0.52
    UNIS
    -0.51
     AU
    -0.51
    POSITIVE LOGITS
    épaisseur
    0.63
    enfance
    0.62
    amitié
    0.62
    échelle
    0.58
    تقاوى
    0.57
    hygiène
    0.56
    ambassade
    0.56
    humanité
    0.54
    entraînement
    0.49
    appui
    0.49
    Act Density 0.707%

    No Known Activations