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

    Neuronpedia

    INDEX
    Explanations

    the phrase "you know," specifically highlighting information or personal insights

    oai_token-act-pair · gpt-3.5-turbo

    instances of repetition or affirmation in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.85
    oslav
    -0.82
    ¬¼
    -0.78
    omal
    -0.76
    Init
    -0.71
    mage
    -0.70
    oreal
    -0.70
    onding
    -0.69
    nai
    -0.69
    ĸļ
    -0.69
    POSITIVE LOGITS
     uh
    0.90
     sir
    0.68
     WHERE
    0.67
     CLASS
    0.64
     Harriet
    0.64
     hed
    0.63
     LET
    0.63
     tick
    0.62
     gentlemen
    0.61
     WHAT
    0.60
    Act Density 0.041%

    No Known Activations