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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inclusivity across various demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.73
    EDEFAULT
    -0.66
     sanno
    -0.58
     _$
    -0.57
     onCreateView
    -0.57
    ContentAsync
    -0.56
     समीक्षाएं
    -0.55
    writerow
    -0.54
     spesa
    -0.52
    SequentialGroup
    -0.52
    POSITIVE LOGITS
     formats
    0.60
     shapes
    0.56
     ages
    0.56
    あらゆる
    0.55
     levels
    0.55
     stages
    0.54
     ranging
    0.54
     Bioaccumulative
    0.54
    den
    0.53
     formality
    0.53
    Act Density 0.405%

    No Known Activations