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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially periods and exclamation points

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a sense of urgency or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glim
    -0.81
     oun
    -0.79
    awei
    -0.75
     quir
    -0.75
     rall
    -0.73
    ailability
    -0.72
    onga
    -0.72
     excav
    -0.68
     appra
    -0.68
     overcl
    -0.68
    POSITIVE LOGITS
     :(
    1.15
     pic
    1.12
     Sorry
    1.11
     :)
    1.09
     Please
    1.05
     Seems
    1.05
     Thanks
    1.04
     Thank
    1.04
     :-)
    1.00
    twitter
    0.98
    Act Density 0.409%

    No Known Activations