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

    Neuronpedia

    INDEX
    Explanations

    references to the term "ai"

    oai_token-act-pair · gpt-3.5-turbo

    words related to artificial intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     parity
    -0.81
     partition
    -0.68
     laps
    -0.67
     Vermont
    -0.64
     therm
    -0.63
     Compton
    -0.62
     sucker
    -0.62
     SPD
    -0.62
     spitting
    -0.61
     RNC
    -0.61
    POSITIVE LOGITS
    ai
    4.26
    aii
    1.92
    ais
    1.56
    hai
    1.50
    ao
    1.49
    AI
    1.45
    ae
    1.41
    iu
    1.38
    eki
    1.34
    oi
    1.34
    Act Density 0.020%

    No Known Activations