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

    Neuronpedia

    INDEX
    Explanations

    words related to senses like taste and physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    words related to taste and sensory experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wired
    -0.71
    ogue
    -0.67
    ucle
    -0.64
    istor
    -0.61
    uclear
    -0.60
    WER
    -0.59
    ocally
    -0.59
    ising
    -0.58
     ignorance
    -0.58
    ãĥ«
    -0.58
    POSITIVE LOGITS
    hetics
    0.87
    ript
    0.87
    lest
    0.87
    lers
    0.85
    ean
    0.80
    roxy
    0.80
    olicy
    0.79
    otle
    0.78
    nces
    0.77
    akespeare
    0.75
    Act Density 0.095%

    No Known Activations