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

    Neuronpedia

    INDEX
    Explanations

    interrogative punctuation marks, specifically questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conclusions
    -0.73
    adic
    -0.73
    ciplinary
    -0.72
     motives
    -0.69
     migration
    -0.69
     homelessness
    -0.69
     beliefs
    -0.69
    onial
    -0.68
     characterization
    -0.68
     motivations
    -0.67
    POSITIVE LOGITS
     Yep
    1.18
     Yeah
    1.08
    Yep
    1.04
     Oops
    1.00
     LOL
    0.98
     wink
    0.91
     Awesome
    0.90
     Oh
    0.89
     Nope
    0.88
     Totally
    0.86
    Act Density 0.387%

    No Known Activations