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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iens
    -0.17
    aina
    -0.15
    slaught
    -0.14
    baÅŁ
    -0.14
    erule
    -0.14
    ÙİاÙĨ
    -0.14
    ież
    -0.14
    ê·Ģ
    -0.14
    BSD
    -0.13
    kul
    -0.13
    POSITIVE LOGITS
    yles
    0.15
    urgeon
    0.15
    linger
    0.15
     Diaz
    0.14
    avi
    0.14
     Yue
    0.14
     UNUSED
    0.13
     Shepherd
    0.13
    abouts
    0.13
    UNUSED
    0.13
    Act Density 0.427%

    No Known Activations