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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CTL
    -0.18
    pend
    -0.15
    wyn
    -0.14
    duk
    -0.14
    indr
    -0.14
    нам
    -0.14
    /render
    -0.14
    eyse
    -0.14
    ãģŃ
    -0.13
     Rendering
    -0.13
    POSITIVE LOGITS
     edin
    0.15
    adir
    0.15
    hid
    0.15
    ovic
    0.15
    elif
    0.14
     Hast
    0.14
    ãĥ³ãĤ¬
    0.13
     McKenzie
    0.13
    DAC
    0.13
     no
    0.13
    Act Density 0.233%

    No Known Activations