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

    Neuronpedia

    INDEX
    Explanations

    reference to notable individuals and their accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     idiots
    -0.35
     stupid
    -0.34
     yay
    -0.34
    Yay
    -0.33
     threatened
    -0.32
     Threatened
    -0.32
     okuyayım
    -0.31
    广大
    -0.31
     pursuant
    -0.31
     provide
    -0.30
    POSITIVE LOGITS
    parsedMessage
    0.77
     recalls
    0.76
     laughs
    0.75
     remembers
    0.75
     chuckles
    0.74
     admits
    0.74
     reminis
    0.74
     grins
    0.73
     confesses
    0.71
     credits
    0.70
    Act Density 0.288%

    No Known Activations