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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "stop" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uju
    -0.18
    cul
    -0.17
    xaa
    -0.17
    kv
    -0.17
    _NOP
    -0.15
    ñana
    -0.15
    eel
    -0.15
    fter
    -0.15
    undles
    -0.14
    estar
    -0.14
    POSITIVE LOGITS
    533
    0.16
    over
    0.16
     ub
    0.15
    285
    0.15
    090
    0.15
    653
    0.15
    insk
    0.15
    stop
    0.14
    NCY
    0.14
    375
    0.14
    Act Density 0.028%

    No Known Activations