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

    Neuronpedia

    INDEX
    Explanations

    references to wild horses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <>",
    -0.52
    帖最后由
    -0.40
    Microkernel
    -0.37
    SneakyThrows
    -0.35
     пун
    -0.35
     noses
    -0.34
    rumah
    -0.34
    BURGH
    -0.34
     Bricks
    -0.34
     inset
    -0.33
    POSITIVE LOGITS
     Wild
    1.33
    Wild
    1.30
     wild
    1.28
    wild
    1.20
     WILD
    1.13
    WILD
    1.09
     salvaje
    0.89
     wilder
    0.84
     sauvage
    0.82
     salvajes
    0.79
    Act Density 0.111%

    No Known Activations