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

    Neuronpedia

    INDEX
    Explanations

    the presence of the name "Les" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ally
    -0.50
    fi
    -0.49
    le
    -0.48
    and
    -0.47
    anda
    -0.47
    at
    -0.47
    e
    -0.46
    def
    -0.46
    ity
    -0.46
    ande
    -0.46
    POSITIVE LOGITS
     les
    0.91
    featureID
    0.81
    Personendaten
    0.79
    Les
    0.77
     Les
    0.75
     lesion
    0.70
    ImageContext
    0.70
     unknownFields
    0.68
     lesions
    0.67
     NSCoder
    0.66
    Act Density 0.527%

    No Known Activations