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

    Neuronpedia

    INDEX
    Explanations

    references to signing documents and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enses
    -0.15
     Sund
    -0.14
    (shader
    -0.13
    Ïħμ
    -0.13
     porad
    -0.13
     Sears
    -0.13
    _SENSOR
    -0.13
    enschaft
    -0.13
    æĸ¯çī¹
    -0.13
    avi
    -0.12
    POSITIVE LOGITS
     sign
    0.93
    -sign
    0.85
     Sign
    0.83
     signing
    0.82
    sign
    0.82
     SIGN
    0.79
    Sign
    0.76
    .sign
    0.75
     signed
    0.74
    _sign
    0.73
    Act Density 0.222%

    No Known Activations