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

    Neuronpedia

    INDEX
    Explanations

    words related to using something for a specific purpose or action

    oai_token-act-pair · gpt-3.5-turbo

    actions and functions related to the use or application of various concepts, objects, or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    option
    -0.67
    soon
    -0.66
    scrib
    -0.64
    rike
    -0.64
     ?)
    -0.62
    sequ
    -0.61
    ogun
    -0.60
    åħī
    -0.59
    anian
    -0.59
    done
    -0.59
    POSITIVE LOGITS
     purposes
    0.81
     efficiently
    0.67
     everyday
    0.66
     subsistence
    0.62
     certain
    0.61
     illegal
    0.61
     various
    0.61
    romptu
    0.60
     Advertisement
    0.59
     behalf
    0.58
    Act Density 0.220%

    No Known Activations