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

    Neuronpedia

    INDEX
    Explanations

    statements about attempts and actions related to deceit or manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uras
    -0.15
    etail
    -0.14
    ARA
    -0.14
    itness
    -0.14
    ara
    -0.13
    SharedPointer
    -0.13
     Imported
    -0.13
    mai
    -0.13
    ovat
    -0.13
    akk
    -0.13
    POSITIVE LOGITS
     curry
    0.29
     please
    0.25
     plac
    0.25
     ing
    0.23
     distance
    0.22
     pac
    0.21
     score
    0.21
     hum
    0.21
     impress
    0.21
     drum
    0.20
    Act Density 0.222%

    No Known Activations