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

    Neuronpedia

    INDEX
    Explanations

    terms related to various categories, such as driving, locations, healthcare, business, social media, education, etc

    oai_token-act-pair · gpt-3.5-turbo

    recurrent mentions of various entities and categories like drivers, children, states, and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stals
    -0.67
     STA
    -0.64
    lua
    -0.61
    shirts
    -0.60
     magnets
    -0.59
    ersive
    -0.58
    ounded
    -0.58
     tongues
    -0.57
     Vers
    -0.56
     Byrd
    -0.56
    POSITIVE LOGITS
     imaginable
    1.35
     conceivable
    0.94
     except
    0.90
     ounce
    0.75
    except
    0.73
     whatsoever
    0.73
    nut
    0.72
    ãĤ«
    0.72
     nodd
    0.71
     individually
    0.70
    Act Density 0.145%

    No Known Activations