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

    Neuronpedia

    INDEX
    Explanations

    numerical measurements of distance in meters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of measurements in meters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Thumbnail
    -0.77
    istically
    -0.76
    =-=-=-=-=-=-=-=-
    -0.71
    itives
    -0.70
    inc
    -0.70
    ãģį
    -0.68
    doms
    -0.66
    ================================================================
    -0.66
    gin
    -0.64
    ãģĭ
    -0.62
    POSITIVE LOGITS
    imet
    0.89
    asonic
    0.89
     Cheong
    0.84
     meters
    0.83
    ometers
    0.77
    unicip
    0.74
    rique
    0.72
    meter
    0.72
     diameter
    0.71
     dash
    0.70
    Act Density 0.009%

    No Known Activations