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

    Neuronpedia

    INDEX
    Explanations

    references to tigers and related imagery or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ..\..\
    -0.45
     Thule
    -0.43
    Sage
    -0.42
    PYX
    -0.42
     Sage
    -0.42
     gog
    -0.41
     crc
    -0.40
     Tuba
    -0.40
    sage
    -0.40
     Shaker
    -0.38
    POSITIVE LOGITS
     Tiger
    1.51
     tiger
    1.46
    Tiger
    1.42
     Tigers
    1.34
     tigers
    1.33
     Lion
    1.29
     lion
    1.27
    Lion
    1.20
     lions
    1.13
     Lions
    1.11
    Act Density 0.515%

    No Known Activations