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

    Neuronpedia

    INDEX
    Explanations

    phrases related to product recalls and safety warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     envelope
    -0.16
    legates
    -0.14
     sil
    -0.14
    amu
    -0.14
     envelopes
    -0.14
    uds
    -0.13
    occo
    -0.13
    ander
    -0.13
     rud
    -0.13
    amel
    -0.13
    POSITIVE LOGITS
    enci
    0.17
    ãĤ«ãĥ¼
    0.15
    cus
    0.15
    Å¡ov
    0.15
    olen
    0.14
    eer
    0.14
    rance
    0.14
     Johnston
    0.14
    unsafe
    0.14
    esto
    0.14
    Act Density 0.045%

    No Known Activations