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

    Neuronpedia

    INDEX
    Explanations

    phrases ending with single quotation marks ('), typically indicating dialogue or direct speech

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks signaling endings or emotional expressions in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sels
    -0.70
    akra
    -0.63
     facilit
    -0.62
    ancies
    -0.61
    asers
    -0.61
    unker
    -0.61
    Ļ½
    -0.60
    ª
    -0.59
    oug
    -0.58
    istries
    -0.58
    POSITIVE LOGITS
    /"
    0.89
     âĢķ
    0.69
     ["
    0.68
     ("
    0.67
    ([
    0.67
     Answer
    0.66
     referring
    0.65
     Similarly
    0.65
     [/
    0.64
     Likewise
    0.64
    Act Density 0.209%

    No Known Activations