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

    Neuronpedia

    INDEX
    Explanations

    instances where a microphone is being used or interacted with in some way

    oai_token-act-pair · gpt-3.5-turbo

    references to microphones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENGTH
    -0.72
    tenance
    -0.72
     Dull
    -0.68
     Spit
    -0.67
    vier
    -0.67
    ACTED
    -0.67
     Unified
    -0.66
    ignment
    -0.66
     Anonymous
    -0.66
    BuyableInstoreAndOnline
    -0.64
    POSITIVE LOGITS
    roman
    1.02
     microphones
    0.98
     mic
    0.97
    ropolitan
    0.93
     microphone
    0.91
    rom
    0.90
    romancer
    0.89
    rics
    0.89
    helle
    0.86
    HAEL
    0.82
    Act Density 0.007%

    No Known Activations