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

    Neuronpedia

    INDEX
    Explanations

    words within a dialogue often followed by quotation marks such as 'I,' 'said,' or 'asked.'

    oai_token-act-pair · gpt-3.5-turbo

    instances of characters speaking or dialogue in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.70
     fres
    -0.69
     undermin
    -0.67
     identity
    -0.64
    utterstock
    -0.63
     wedd
    -0.63
     representation
    -0.63
    oÄŁ
    -0.62
     moder
    -0.61
     helicop
    -0.60
    POSITIVE LOGITS
    ³³³³³³³³
    1.08
    ³³³
    1.05
    ³³³³
    1.01
    "...
    0.96
    "âĢ¦
    0.92
    ::::::::
    0.89
    ³³³³³³³³³³³³³³³³
    0.85
    "-
    0.84
    xxxxxxxx
    0.83
    Suddenly
    0.82
    Act Density 0.123%

    No Known Activations