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

    Neuronpedia

    INDEX
    Explanations

    actions related to physical movement, specifically climbing

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to climbing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Hart
    -0.79
    ãĥĨãĤ£
    -0.76
    rums
    -0.76
    pora
    -0.72
    rum
    -0.70
    invoke
    -0.68
    tering
    -0.68
    oral
    -0.67
    gren
    -0.66
    Policy
    -0.64
    POSITIVE LOGITS
     Everest
    1.01
     footh
    1.00
     stairs
    0.98
     climbing
    0.94
     climbers
    0.94
     aboard
    0.87
     climb
    0.84
     ladder
    0.82
     climbs
    0.80
     mountains
    0.78
    Act Density 0.032%

    No Known Activations