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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of quantity or extent

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating quantities or measurements related to actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    notation
    -0.78
    notations
    -0.76
     craw
    -0.68
    rer
    -0.68
    col
    -0.67
    ursor
    -0.66
    onda
    -0.66
    TL
    -0.65
    rend
    -0.64
    nex
    -0.64
    POSITIVE LOGITS
     equivalent
    0.72
     perfection
    0.70
     insign
    0.68
     mere
    0.66
     superhuman
    0.65
    Interstitial
    0.64
     gib
    0.64
     obscene
    0.64
     heresy
    0.64
     extortion
    0.64
    Act Density 0.088%

    No Known Activations