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

    Neuronpedia

    INDEX
    Explanations

    mentions of mountains or specific mountain names

    oai_token-act-pair · gpt-3.5-turbo

    references to mountains, particularly their names and elevations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.79
    razil
    -0.75
    xx
    -0.70
    اÙĦ
    -0.69
    âĸĪâĸĪ
    -0.67
    rx
    -0.66
    ÙIJ
    -0.65
    ersive
    -0.65
    chnology
    -0.64
    axter
    -0.63
    POSITIVE LOGITS
    mount
    0.96
     Sinai
    0.95
     Mount
    0.90
    Mount
    0.84
    aint
    0.83
     Island
    0.83
    aine
    0.81
     Everest
    0.81
    castle
    0.80
    itions
    0.76
    Act Density 0.008%

    No Known Activations