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

    Neuronpedia

    INDEX
    Explanations

    places or locations prefixed with "across"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "across."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FORE
    -0.74
    nery
    -0.73
    rw
    -0.70
    liest
    -0.69
    nce
    -0.67
     psychiat
    -0.63
    rics
    -0.63
    za
    -0.62
    lein
    -0.62
    ns
    -0.62
    POSITIVE LOGITS
    roads
    0.80
    atform
    0.75
     rooft
    0.75
    loading
    0.72
     borders
    0.70
    side
    0.69
    plain
    0.69
    oin
    0.68
    pread
    0.66
    country
    0.66
    Act Density 0.027%

    No Known Activations