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

    Neuronpedia

    INDEX
    Explanations

    terms indicating interruption or disturbance to processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    haul
    -0.19
    ows
    -0.19
    borg
    -0.17
    ause
    -0.16
    gie
    -0.16
    ÛĮزÛĮ
    -0.15
    amburger
    -0.15
    wick
    -0.15
    bay
    -0.15
    ots
    -0.15
    POSITIVE LOGITS
    /dist
    0.24
    ive
    0.21
    ively
    0.18
    eur
    0.18
    iveness
    0.16
    ible
    0.16
    ois
    0.16
     disturbed
    0.15
    amente
    0.15
    edImage
    0.15
    Act Density 0.030%

    No Known Activations