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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events being done through a specific means or process

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports statistics, seasons, and competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ournal
    -0.74
    nai
    -0.67
    pi
    -0.65
    Temperature
    -0.64
    sup
    -0.63
    Percent
    -0.61
     Prix
    -0.60
    DO
    -0.60
     Temper
    -0.59
    DEF
    -0.59
    POSITIVE LOGITS
     channels
    0.92
     prism
    0.88
     intermedi
    0.86
     maze
    0.84
     tunnels
    0.83
     labyrinth
    0.81
     veins
    0.80
     intermediary
    0.78
     loops
    0.78
     lens
    0.77
    Act Density 0.277%

    No Known Activations