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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word 'bot'

    oai_token-act-pair · gpt-3.5-turbo

    references to bots and bot-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barg
    -0.65
     Institution
    -0.63
    dress
    -0.61
     Trib
    -0.60
    mble
    -0.60
     Piercing
    -0.59
     Vie
    -0.58
    ׾
    -0.58
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.57
     jerk
    -0.56
    POSITIVE LOGITS
    anical
    1.74
    anic
    1.33
    any
    1.26
    ania
    1.16
    cham
    1.16
    nets
    1.07
    ulin
    1.01
    herer
    1.00
    zeb
    0.98
    anie
    0.97
    Act Density 0.019%

    No Known Activations