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

    Neuronpedia

    INDEX
    Explanations

    proper nouns starting with 'Is'

    oai_token-act-pair · gpt-3.5-turbo

    the word "Is"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĮ
    -0.82
    theless
    -0.78
    è¦ļéĨĴ
    -0.69
    ruciating
    -0.66
    ilight
    -0.66
    è£
    -0.64
    åij
    -0.62
     markings
    -0.61
     takedown
    -0.60
     stitches
    -0.60
    POSITIVE LOGITS
    olated
    1.43
    olation
    1.30
    abella
    1.25
    peria
    1.21
    olate
    1.19
    htar
    1.15
    sei
    1.06
    ilon
    1.05
    ync
    1.04
    senal
    1.03
    Act Density 0.046%

    No Known Activations