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

    Neuronpedia

    INDEX
    Explanations

    explanations or reasons for various observed phenomena or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate explanations for various phenomena or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sha
    -0.82
    abase
    -0.76
    heit
    -0.70
    umbing
    -0.69
    ubs
    -0.68
    liga
    -0.68
    iaries
    -0.67
    feld
    -0.67
    onds
    -0.66
    reau
    -0.66
    POSITIVE LOGITS
     existence
    0.91
     downfall
    0.91
     discrepancies
    0.91
     deaths
    0.88
     emergence
    0.86
     reluctance
    0.86
     demise
    0.86
     genesis
    0.85
     instability
    0.84
     uptick
    0.82
    Act Density 0.269%

    No Known Activations