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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quantities or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of comparisons involving the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UCT
    -0.66
    istries
    -0.66
    uctions
    -0.65
     Dism
    -0.61
     Advocate
    -0.60
     Mou
    -0.60
     largeDownload
    -0.59
    -0.58
     âĨ
    -0.58
    urai
    -0.58
    POSITIVE LOGITS
    cells
    0.75
    thus
    0.72
    nir
    0.70
    tes
    0.67
     traditionally
    0.66
    iably
    0.66
     necessarily
    0.66
     ever
    0.65
    pees
    0.65
    anyl
    0.64
    Act Density 0.112%

    No Known Activations