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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating misunderstanding or misconceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inate
    -0.16
    late
    -0.15
    ccak
    -0.14
    tsky
    -0.14
    unar
    -0.14
     marque
    -0.14
     Incontri
    -0.14
    inition
    -0.14
    omat
    -0.14
    entiful
    -0.14
    POSITIVE LOGITS
     con
    0.18
     ven
    0.16
     refin
    0.15
    edly
    0.15
    764
    0.15
    Occurred
    0.15
     Leslie
    0.14
     Commons
    0.14
     condition
    0.14
     alike
    0.14
    Act Density 0.152%

    No Known Activations