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

    Neuronpedia

    INDEX
    Explanations

    references to scientific research and academic authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utto
    -0.16
     tay
    -0.16
    ãģķ
    -0.16
     Choi
    -0.15
     Gi
    -0.15
     ver
    -0.15
    ar
    -0.15
     --
    -0.15
    -0.15
    ...
    -0.14
    POSITIVE LOGITS
     Lv
    0.19
    allen
    0.19
    liÄį
    0.18
     LENG
    0.17
    ¡´
    0.17
    èĥľ
    0.16
    SSERT
    0.16
    lili
    0.16
    çĶ³åįļ
    0.15
     X
    0.15
    Act Density 0.060%

    No Known Activations