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

    Neuronpedia

    INDEX
    Explanations

    quantitative limits or thresholds

    oai_token-act-pair · gpt-3.5-turbo

    specific conditions, limitations, or parameters that lead to significant consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Joined
    -0.64
    Advertisements
    -0.57
     hemor
    -0.56
    Screenshot
    -0.55
    resa
    -0.54
    Sit
    -0.54
    Reader
    -0.53
     Span
    -0.53
     Folk
    -0.53
     Redmond
    -0.53
    POSITIVE LOGITS
     implies
    1.21
     undermines
    1.14
     requires
    1.14
     constitutes
    1.13
     ensures
    1.12
     occurs
    1.12
     involves
    1.07
     entails
    1.06
     tends
    1.06
     signifies
    1.04
    Act Density 0.553%

    No Known Activations