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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals, especially in academic or scholarly contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     safe
    -0.28
     spirit
    -0.25
     základ
    -0.24
    发表于
    -0.24
     cor
    -0.24
     كث
    -0.23
     jie
    -0.22
     espíritu
    -0.22
    Enrico
    -0.21
    ävän
    -0.21
    POSITIVE LOGITS
     tartalomajánló
    0.72
    exitRule
    0.68
     autorytatywna
    0.65
    RenderAtEndOf
    0.63
     müſſen
    0.63
    majánló
    0.60
    ronpa
    0.60
     Vital
    0.60
     ſehr
    0.59
    ᥀
    0.59
    Act Density 0.221%

    No Known Activations