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

    Neuronpedia

    INDEX
    Explanations

    the word "and"

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odcast
    -0.75
     tremend
    -0.74
     eleph
    -0.70
     ferment
    -0.69
    lectic
    -0.68
     satell
    -0.67
    mpeg
    -0.67
    pmwiki
    -0.65
     fasc
    -0.65
    keley
    -0.64
    POSITIVE LOGITS
    erers
    1.11
    hra
    1.03
    idate
    1.01
    erer
    1.01
    rogen
    0.93
    romeda
    0.90
    ering
    0.90
    emonium
    0.89
    ered
    0.88
    ahar
    0.87
    Act Density 0.036%

    No Known Activations