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

    Neuronpedia

    INDEX
    Explanations

    references to microphones

    oai_token-act-pair · gpt-3.5-turbo

    mentions of microphones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Spit
    -0.84
    tenance
    -0.82
    ENGTH
    -0.76
     Unified
    -0.70
    ACTED
    -0.69
     Dull
    -0.67
    CLASSIFIED
    -0.67
    ignment
    -0.67
    ãģĦ
    -0.67
     Pact
    -0.65
    POSITIVE LOGITS
    roman
    1.06
    helle
    1.00
    ropolitan
    0.99
    romancer
    0.96
    rom
    0.91
    asonic
    0.86
    rics
    0.85
    rodu
    0.84
    rones
    0.83
    rop
    0.82
    Act Density 0.011%

    No Known Activations