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

    Neuronpedia

    INDEX
    Explanations

    references to groups of people or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.31
    (es
    -0.16
    ayne
    -0.16
     its
    -0.15
    quine
    -0.14
    ãĤ¹ãĥŀ
    -0.14
    ÑĹ
    -0.14
    irection
    -0.14
    ering
    -0.13
    اÙĨÙĩ
    -0.13
    POSITIVE LOGITS
    /us
    0.41
    /her
    0.30
    self
    0.29
    atically
    0.28
     themselves
    0.25
    /th
    0.25
    /we
    0.24
    elves
    0.24
    iner
    0.23
    zelf
    0.23
    Act Density 0.097%

    No Known Activations