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

    Neuronpedia

    INDEX
    Explanations

    words related to official titles or positions

    oai_token-act-pair · gpt-3.5-turbo

    the plural form of the letter "s."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    service
    -0.63
    ifix
    -0.63
    epad
    -0.62
    esp
    -0.61
    docker
    -0.60
     Canaver
    -0.59
    adjust
    -0.59
    event
    -0.59
    dress
    -0.58
    opens
    -0.58
    POSITIVE LOGITS
    pecially
    0.85
     tallest
    0.84
    outhern
    0.82
     birthplace
    0.79
    selves
    0.77
     premier
    0.76
    wered
    0.75
     poorest
    0.75
    ources
    0.73
     largest
    0.73
    Act Density 0.155%

    No Known Activations