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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific organizations or individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the preposition "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    respective
    -0.72
     collateral
    -0.68
    required
    -0.68
     placeholder
    -0.66
     accordingly
    -0.66
     peripher
    -0.65
     entit
    -0.64
     dehuman
    -0.63
     categor
    -0.63
     deval
    -0.63
    POSITIVE LOGITS
     Alexandria
    0.91
     Georgetown
    0.90
     Bellev
    0.88
    icial
    0.85
     Providence
    0.83
     Anaheim
    0.82
     Syracuse
    0.81
    sky
    0.81
     Bethlehem
    0.79
     Wilmington
    0.79
    Act Density 0.044%

    No Known Activations