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

    Neuronpedia

    INDEX
    Explanations

    items tied to a specific physical attribute, specifically those that are slick and smooth

    oai_token-act-pair · gpt-3.5-turbo

    instances of the string "sl"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleas
    -0.68
    bell
    -0.64
     directions
    -0.63
     Nam
    -0.62
    IFIC
    -0.62
    lde
    -0.61
     Sons
    -0.58
    wealth
    -0.58
    enegger
    -0.57
     Haas
    -0.57
    POSITIVE LOGITS
    anted
    1.19
    asher
    1.18
    udge
    1.16
    inging
    1.15
    otted
    1.14
    ashes
    1.13
    ugg
    1.13
    umping
    1.10
    ighter
    1.08
    ippery
    1.07
    Act Density 0.023%

    No Known Activations