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

    Neuronpedia

    INDEX
    Explanations

    concepts related to challenging societal norms and stereotypes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .MixedReality
    -0.16
    638
    -0.15
    rana
    -0.14
    amerate
    -0.14
     INTERVAL
    -0.14
    constitutional
    -0.14
    ysl
    -0.13
    iec
    -0.13
    qrst
    -0.13
    cef
    -0.13
    POSITIVE LOGITS
     conventional
    0.46
     convention
    0.44
     established
    0.41
     conventions
    0.40
     traditional
    0.39
     establishment
    0.36
     orth
    0.35
     accepted
    0.34
     Convention
    0.33
     norms
    0.33
    Act Density 0.345%

    No Known Activations