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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "detection" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    i
    -0.83
    addFlags
    -0.78
     whole
    -0.72
    ي
    -0.68
     Mindy
    -0.67
     Winder
    -0.64
    li
    -0.64
    zele
    -0.64
     Thore
    -0.64
    oro
    -0.63
    POSITIVE LOGITS
     DETECTION
    1.12
     Detect
    1.07
     detectors
    1.04
     DETECT
    1.03
     detections
    1.02
     Detectors
    1.02
    DETECT
    1.02
    pośred
    1.00
     Dete
    1.00
     Detected
    0.98
    Act Density 0.187%

    No Known Activations