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

    Neuronpedia

    INDEX
    Explanations

    mentions of LGBT Pride events and related figures, particularly Taylor Swift

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umer
    -0.16
    ritz
    -0.16
    zin
    -0.15
    raj
    -0.15
    ooth
    -0.15
     collapse
    -0.15
     wasted
    -0.14
     Collapse
    -0.14
    ä¸ĸ
    -0.14
    autoload
    -0.13
    POSITIVE LOGITS
     Reputation
    0.25
     Tay
    0.22
     Folk
    0.21
    aylor
    0.21
     Taylor
    0.20
     tay
    0.20
    Taylor
    0.19
     Swift
    0.19
     Shake
    0.18
    Swift
    0.18
    Act Density 0.007%

    No Known Activations