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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical climbing

    oai_token-act-pair · gpt-3.5-turbo

    references to climbing activities or related actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    invoke
    -0.72
    actionDate
    -0.70
    gren
    -0.68
    nesota
    -0.65
    esson
    -0.63
    eren
    -0.63
    aments
    -0.63
    ersive
    -0.63
    rums
    -0.62
    Ĭ±
    -0.62
    POSITIVE LOGITS
     Everest
    1.18
     stairs
    1.09
     footh
    1.04
     climbing
    1.02
     ladder
    1.00
     aboard
    0.99
     climb
    0.99
     ascent
    0.95
     climbs
    0.92
     mountains
    0.91
    Act Density 0.056%

    No Known Activations