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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the term "Is" followed by certain words or symbols

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "Is"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     XD
    -0.67
    IOR
    -0.67
     phrase
    -0.66
    theless
    -0.63
     excise
    -0.62
     enterprises
    -0.61
     institute
    -0.61
     denomin
    -0.59
    ĸļ
    -0.59
     digs
    -0.59
    POSITIVE LOGITS
    abella
    1.50
    olated
    1.49
    olation
    1.47
    olate
    1.39
    abel
    1.35
    hma
    1.27
    peria
    1.24
    sei
    1.23
    mail
    1.22
    lington
    1.19
    Act Density 0.057%

    No Known Activations