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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to the foundational concept on which something is based

    oai_token-act-pair · gpt-3.5-turbo

    variations of the concept of "premise."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sung
    -0.98
    thumbnails
    -0.75
    haps
    -0.71
    ansk
    -0.71
    adder
    -0.69
    ocker
    -0.69
    hner
    -0.69
    aina
    -0.68
    pine
    -0.68
    icer
    -0.68
    POSITIVE LOGITS
     premise
    1.24
     proposition
    0.88
    ioned
    0.80
     assumption
    0.80
     underpin
    0.78
    eers
    0.77
     premises
    0.76
    ually
    0.73
     creep
    0.68
     hog
    0.67
    Act Density 0.033%

    No Known Activations