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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mnoho
    -0.68
     lecz
    -0.60
     gyermek
    -0.59
     bowiem
    -0.56
     indeed
    -0.56
     lamang
    -0.54
    許多
    -0.54
     perhaps
    -0.54
    indeed
    -0.53
    许多
    -0.52
    POSITIVE LOGITS
     dude
    1.17
     dudes
    1.14
     weird
    1.00
     kinda
    1.00
     guy
    0.96
     guys
    0.94
     GUYS
    0.90
     Dude
    0.90
     freaked
    0.89
     fuckin
    0.88
    Act Density 0.457%

    No Known Activations