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

    Neuronpedia

    INDEX
    Explanations

    terms related to audiovisual (AV) technology

    oai_token-act-pair · gpt-3.5-turbo

    references to autonomous vehicles (AV)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tons
    -0.76
     constant
    -0.72
     Coke
    -0.71
     lamb
    -0.68
    kick
    -0.66
     speaking
    -0.66
    rition
    -0.66
    spection
    -0.65
     padd
    -0.65
     mercury
    -0.64
    POSITIVE LOGITS
    AV
    0.98
    irtual
    0.94
    atars
    0.93
    PLIC
    0.91
    ILLE
    0.87
    iew
    0.86
    ILE
    0.85
    INO
    0.84
    LP
    0.81
    icular
    0.80
    Act Density 0.005%

    No Known Activations