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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions, obligations, or specifications in legal or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    351
    -0.16
     D
    -0.14
    ele
    -0.14
    semb
    -0.14
     familiar
    -0.13
    872
    -0.13
     Boy
    -0.13
    alsy
    -0.13
     Vance
    -0.13
    ฤ
    -0.13
    POSITIVE LOGITS
    agua
    0.17
    ex
    0.16
    ocado
    0.16
    TEE
    0.16
    uo
    0.15
    obe
    0.15
    εÏĦ
    0.14
    chop
    0.14
    abox
    0.14
    ãĤ¤ãĥĦ
    0.14
    Act Density 0.060%

    No Known Activations