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

    Neuronpedia

    INDEX
    Explanations

    modifiers and conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of casual conversation or transitions in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ascript
    -0.75
    è¦ļéĨĴ
    -0.71
    natureconservancy
    -0.68
    reated
    -0.66
    à¨
    -0.65
    nai
    -0.65
    angering
    -0.64
    externalActionCode
    -0.64
    ngth
    -0.62
    Pokémon
    -0.61
    POSITIVE LOGITS
     bye
    0.84
    bye
    0.77
     Wrong
    0.75
     congratulations
    0.69
     yeah
    0.66
     Sorry
    0.65
    yeah
    0.65
     goodbye
    0.65
     maybe
    0.65
     excuse
    0.64
    Act Density 0.051%

    No Known Activations