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

    Neuronpedia

    INDEX
    Explanations

    mentions of material or substances like paint, lacquer, or ink

    oai_token-act-pair · gpt-3.5-turbo

    attributes and characteristics related to physical products or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     convened
    -0.73
     Liberal
    -0.71
     Samar
    -0.68
     Ethics
    -0.68
     Assange
    -0.66
     Yiannopoulos
    -0.66
     Trudeau
    -0.65
     Fiscal
    -0.65
     stewards
    -0.65
     leadership
    -0.64
    POSITIVE LOGITS
     thickness
    1.03
     protr
    0.96
     bulky
    0.96
     thicker
    0.93
     casing
    0.92
     moisture
    0.89
     texture
    0.88
     curv
    0.86
     seams
    0.85
     waterproof
    0.84
    Act Density 1.193%

    No Known Activations