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

    Neuronpedia

    INDEX
    Explanations

    words related to medical substances or chemical compounds

    oai_token-act-pair · gpt-3.5-turbo

    chemical substances and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     outstanding
    -0.72
     appearance
    -0.65
     orig
    -0.64
     autos
    -0.60
     event
    -0.60
     Kov
    -0.59
     ar
    -0.59
     Torn
    -0.59
     unc
    -0.59
     CC
    -0.58
    POSITIVE LOGITS
    rine
    5.00
    rone
    1.81
    rin
    1.73
    rina
    1.48
    leen
    1.29
    robe
    1.16
    rogens
    1.12
    ril
    1.11
    rette
    1.09
    riel
    1.07
    Act Density 0.014%

    No Known Activations