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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating record achievements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isan
    -0.16
    ardin
    -0.16
    inch
    -0.14
    Unexpected
    -0.14
     ust
    -0.14
    plied
    -0.13
    yc
    -0.13
    aves
    -0.13
    stants
    -0.13
    /internal
    -0.13
    POSITIVE LOGITS
    -breaking
    0.47
    breaking
    0.44
     breaking
    0.40
    -setting
    0.40
     Breaking
    0.35
    Breaking
    0.34
    setting
    0.31
     breaker
    0.30
    -break
    0.29
     setting
    0.29
    Act Density 0.017%

    No Known Activations