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

    Neuronpedia

    INDEX
    Explanations

    words related to chemical compounds

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "ron" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apart
    -0.68
     mosqu
    -0.66
     entangled
    -0.63
     diffuse
    -0.63
     versa
    -0.63
     victimized
    -0.61
     adolesc
    -0.61
     Afgh
    -0.59
     %%
    -0.59
     fragile
    -0.58
    POSITIVE LOGITS
    ron
    4.56
    rons
    2.82
    RON
    2.43
    ronic
    1.90
    rone
    1.68
    rones
    1.47
    ronics
    1.41
    ros
    1.39
    rom
    1.37
    ront
    1.36
    Act Density 0.013%

    No Known Activations