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

    Neuronpedia

    INDEX
    Explanations

    references to the activity of surfing

    oai_token-act-pair · gpt-3.5-turbo

    references to surfing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Innocent
    -0.81
    oyer
    -0.80
    lethal
    -0.71
     Means
    -0.71
    cius
    -0.70
    erker
    -0.69
    claw
    -0.68
    ogical
    -0.67
    wagen
    -0.67
    mberg
    -0.67
    POSITIVE LOGITS
     surf
    4.14
     surfing
    3.04
     Surf
    2.74
     skate
    1.44
     swim
    1.32
     beach
    1.22
     beaches
    1.18
     paddle
    1.18
     sunscreen
    1.14
     swell
    1.10
    Act Density 0.016%

    No Known Activations