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

    Neuronpedia

    INDEX
    Explanations

    references to sign language and deaf culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alah
    -0.16
    uste
    -0.15
    iad
    -0.14
    lice
    -0.14
    rede
    -0.14
    933
    -0.14
    課
    -0.13
    xious
    -0.13
    æ¡£
    -0.13
    eter
    -0.13
    POSITIVE LOGITS
     deaf
    0.45
     sign
    0.44
     signing
    0.43
     Signing
    0.42
     Signed
    0.40
     Sign
    0.39
     signer
    0.39
    Signing
    0.38
     signed
    0.38
    Signed
    0.36
    Act Density 0.019%

    No Known Activations