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

    Neuronpedia

    INDEX
    Explanations

    descriptors that indicate positive qualities or reputations associated with people, places, or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    ØŃÙĩ
    -0.14
     booty
    -0.14
    istrat
    -0.14
    å¸Ń
    -0.14
    atr
    -0.14
    indy
    -0.14
     ëĮĢìĥģ
    -0.13
    uyla
    -0.13
    .Rendering
    -0.13
    POSITIVE LOGITS
    lox
    0.16
    ÑĢол
    0.15
    ly
    0.15
    roscope
    0.14
    edin
    0.13
    intr
    0.13
    letal
    0.13
     Ya
    0.13
    bral
    0.13
    egen
    0.13
    Act Density 0.135%

    No Known Activations