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

    Neuronpedia

    INDEX
    Explanations

    the word "girl"

    oai_token-act-pair · gpt-3.5-turbo

    mentions or references related to the character "Pirl."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tones
    -0.68
     mitigation
    -0.67
     persuasion
    -0.65
     tone
    -0.64
     electrode
    -0.63
     electrodes
    -0.63
     repentance
    -0.63
     line
    -0.61
     Moral
    -0.61
     admissions
    -0.60
    POSITIVE LOGITS
    irl
    4.91
    irling
    1.80
    irled
    1.48
    irst
    1.24
    irlwind
    1.22
    irlf
    1.12
    irc
    1.11
    irs
    1.01
    irt
    1.01
     Airl
    0.99
    Act Density 0.013%

    No Known Activations