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

    Neuronpedia

    INDEX
    Explanations

    references to duality or comparisons between pairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    czy
    -0.16
    ient
    -0.15
    aja
    -0.15
    xit
    -0.15
    gne
    -0.14
    gro
    -0.14
    imate
    -0.13
    few
    -0.13
    lah
    -0.13
    ow
    -0.13
    POSITIVE LOGITS
    ymm
    0.14
    ERIC
    0.14
    éĢ¸
    0.14
     полÑı
    0.14
     mình
    0.14
     Bott
    0.13
    conti
    0.13
    訳
    0.13
     controversial
    0.13
    plet
    0.13
    Act Density 0.028%

    No Known Activations