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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical climbing or ascending

    oai_token-act-pair · gpt-3.5-turbo

    terms related to climbing activities and movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    invoke
    -0.76
    ãĥĨãĤ£
    -0.73
    gren
    -0.70
    oral
    -0.70
    esson
    -0.68
    actionDate
    -0.67
    istration
    -0.67
    eren
    -0.66
    aments
    -0.65
    ãĥĩãĤ£
    -0.64
    POSITIVE LOGITS
     Everest
    1.04
     footh
    1.04
     stairs
    0.99
     ladder
    0.98
     climbing
    0.97
     climb
    0.95
     aboard
    0.95
     climbs
    0.93
     mountains
    0.92
     climbers
    0.89
    Act Density 0.074%

    No Known Activations