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

    Neuronpedia

    INDEX
    Explanations

    punctuation and quotes to signal dialogue or expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indeed
    -0.19
    Indeed
    -0.15
     tomorrow
    -0.15
     tod
    -0.15
     today
    -0.14
    inde
    -0.14
     BELOW
    -0.14
     perhaps
    -0.14
     below
    -0.14
    PLEASE
    -0.14
    POSITIVE LOGITS
     Growing
    0.21
    Growing
    0.20
     [
    0.19
     Working
    0.19
    Working
    0.17
    laughs
    0.17
     Plus
    0.17
     Me
    0.17
     Meeting
    0.17
     I
    0.17
    Act Density 0.095%

    No Known Activations