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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds and elements

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of substances and their properties or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburg
    -0.76
    edIn
    -0.70
    edin
    -0.69
     è£ıè
    -0.68
    ibl
    -0.68
     congr
    -0.67
    uctor
    -0.66
    ablishment
    -0.64
    intent
    -0.64
    */
    -0.63
    POSITIVE LOGITS
     commonly
    1.23
     considered
    1.15
     widely
    1.15
     believed
    1.11
     known
    1.08
     marketed
    1.07
     traditionally
    1.05
     regarded
    1.05
     derived
    1.04
     characterized
    1.03
    Act Density 0.183%

    No Known Activations