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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating dialogue or spoken words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     =>
    -0.59
    -
    -0.55
     (
    -0.52
    ?
    -0.52
    Viitteet
    -0.51
     numberWith
    -0.51
     المعيارى
    -0.50
    følgelig
    -0.50
    --
    -0.49
    وردار
    -0.49
    POSITIVE LOGITS
    <bos>
    1.23
    Autoritní
    1.04
    sizeCache
    0.99
    rungsseite
    0.94
     kaarangay
    0.93
    ArrowToggle
    0.90
    Vidite
    0.86
     ainfi
    0.86
    OGND
    0.83
     feroit
    0.81
    Act Density 0.597%

    No Known Activations