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

    Neuronpedia

    INDEX
    Explanations

    mentions of academic titles or degrees

    oai_token-act-pair · gpt-3.5-turbo

    instances of the indefinite article "a" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atcher
    -0.70
    sheets
    -0.69
    lins
    -0.68
    tests
    -0.68
    Upload
    -0.67
     Jagu
    -0.67
    aneously
    -0.67
    !!!!!
    -0.66
    nesday
    -0.66
    Fer
    -0.65
    POSITIVE LOGITS
     penchant
    1.08
     knack
    1.03
     tendency
    0.99
     propensity
    0.99
     lot
    0.95
     vested
    0.92
     bunch
    0.87
     strong
    0.86
     sizable
    0.86
     definite
    0.85
    Act Density 0.185%

    No Known Activations