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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific geographical features, especially mountains

    oai_token-act-pair · gpt-3.5-turbo

    references to mountains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Machina
    -0.84
    uel
    -0.83
    BACK
    -0.83
    NER
    -0.79
    lest
    -0.78
    encia
    -0.77
    âĸ¬
    -0.76
    Interstitial
    -0.75
    ually
    -0.74
    furt
    -0.74
    POSITIVE LOGITS
     biking
    1.09
     mountain
    0.93
     laure
    0.87
     ridge
    0.86
     climbers
    0.86
     footh
    0.85
     mountains
    0.84
     skiing
    0.82
     climbing
    0.82
     Sinai
    0.81
    Act Density 0.020%

    No Known Activations