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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a conjunction or connection between two entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.78
     WARN
    -0.68
    lectic
    -0.68
    keley
    -0.67
    odcast
    -0.67
    ¥µ
    -0.65
    AMS
    -0.65
     fasc
    -0.64
    mpeg
    -0.64
     eleph
    -0.62
    POSITIVE LOGITS
    idate
    1.04
    romeda
    1.01
    hra
    0.96
    rogen
    0.96
    rew
    0.94
    ean
    0.93
    rea
    0.91
    inav
    0.90
    erers
    0.89
    ahar
    0.89
    Act Density 0.037%

    No Known Activations