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

    Neuronpedia

    INDEX
    Explanations

    phrases containing speech-related words or direct quotes

    oai_token-act-pair · gpt-3.5-turbo

    instances of expressive or emotionally charged dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artifacts
    -0.89
    issance
    -0.84
    olicy
    -0.82
    emis
    -0.79
    profits
    -0.76
    ropolis
    -0.76
    cair
    -0.75
    hesda
    -0.75
    etheless
    -0.74
    dates
    -0.74
    POSITIVE LOGITS
     whisper
    1.17
     understatement
    1.17
     voice
    1.16
     loud
    1.14
     plaint
    1.12
     tone
    1.12
     tones
    1.10
     sarcastic
    1.09
     chorus
    1.06
     tongue
    1.05
    Act Density 0.173%

    No Known Activations