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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "As" to indicate conditional or contextual statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     evidenced
    -0.16
    .ua
    -0.16
     Rosenstein
    -0.15
    atti
    -0.14
    stm
    -0.14
    ÚĺÙĨ
    -0.14
    ì§Ŀ
    -0.14
    _PR
    -0.14
    sep
    -0.13
    ogan
    -0.13
    POSITIVE LOGITS
    orro
    0.16
    ê°IJ
    0.15
    PEND
    0.15
    omi
    0.15
    alom
    0.15
    γκα
    0.15
    mî
    0.14
    -Sah
    0.14
     suk
    0.14
    andard
    0.14
    Act Density 0.054%

    No Known Activations