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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    completely empty sections or gaps in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iology
    -0.91
    ivalent
    -0.85
    icans
    -0.85
    ysis
    -0.81
    iguous
    -0.76
    ienne
    -0.76
    ulous
    -0.76
    ican
    -0.76
    vier
    -0.76
    isers
    -0.75
    POSITIVE LOGITS
    pling
    0.86
     sqor
    0.77
    cha
    0.73
    oway
    0.72
    PIN
    0.70
    plings
    0.67
    eca
    0.66
    urities
    0.65
    pixel
    0.64
    OTA
    0.64
    Act Density 0.053%

    No Known Activations