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

    Neuronpedia

    INDEX
    Explanations

    words related to mountains

    oai_token-act-pair · gpt-3.5-turbo

    references to mountains and related landscapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tle
    -0.78
    orate
    -0.75
    lich
    -0.73
    ··
    -0.73
    zig
    -0.68
    ifice
    -0.67
    tons
    -0.66
    istry
    -0.66
    lest
    -0.66
    sembly
    -0.64
    POSITIVE LOGITS
     biking
    1.22
     climbers
    1.01
     ridge
    0.96
     ranges
    0.91
     footh
    0.91
     Everest
    0.89
     lion
    0.88
     slopes
    0.88
     climbing
    0.87
     laure
    0.86
    Act Density 0.043%

    No Known Activations