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

    Neuronpedia

    INDEX
    Explanations

    patterns of repetition and connections between ideas in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urf
    -0.17
    esk
    -0.16
    ored
    -0.16
    ÏĦία
    -0.15
     ë§İìĿ´
    -0.14
    reon
    -0.14
    isty
    -0.13
    usk
    -0.13
    oder
    -0.13
    ached
    -0.13
    POSITIVE LOGITS
     vo
    0.46
     guess
    0.41
     sure
    0.38
     Vo
    0.37
    guess
    0.34
    vo
    0.34
     Sure
    0.33
     lo
    0.33
     prest
    0.33
     Guess
    0.33
    Act Density 0.275%

    No Known Activations