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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "called" followed by a noun

    oai_token-act-pair · gpt-4-turbo

    proper nouns or technical terms with an emphasis on the word "called"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "called."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     istg
    -0.76
    inth
    -0.76
    andowski
    -0.74
    bilt
    -0.69
    itars
    -0.67
     Column
    -0.65
    Lago
    -0.65
    =-=-
    -0.63
    ipeg
    -0.61
    ORTS
    -0.61
    POSITIVE LOGITS
    call
    0.95
    calling
    0.95
     called
    0.89
    called
    0.85
     calling
    0.83
    backs
    0.72
    interstitial
    0.72
     Calling
    0.72
     Call
    0.71
    comings
    0.70
    Act Density 0.048%

    No Known Activations