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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exhaustion or depletion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    running out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rond
    -0.50
    componentWill
    -0.50
     thereupon
    -0.48
    appcompat
    -0.48
    complexContent
    -0.47
    RegressionTest
    -0.46
     Stands
    -0.46
     graciously
    -0.45
    <_>
    -0.43
     panel
    -0.42
    POSITIVE LOGITS
     ſeveral
    0.55
     repuesto
    0.52
    hilangan
    0.49
     uſed
    0.48
     myſelf
    0.48
     Theſe
    0.47
     disambiguazione
    0.47
     genügend
    0.47
     leſs
    0.46
     occaf
    0.45
    Act Density 0.010%

    No Known Activations