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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical locations, specifically those ending in "-est"

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases that involve a form of the word "pedestrian."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.74
    perty
    -0.70
    chwitz
    -0.69
    awaru
    -0.66
    keyes
    -0.65
     tremend
    -0.63
    pton
    -0.63
     turnover
    -0.63
     Moroc
    -0.61
     racked
    -0.59
    POSITIVE LOGITS
    est
    1.10
    hest
    1.03
    ruct
    0.97
    owe
    0.95
    ream
    0.93
    imate
    0.92
    imated
    0.88
    eal
    0.85
    imates
    0.84
    ests
    0.84
    Act Density 0.014%

    No Known Activations