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

    Neuronpedia

    INDEX
    Explanations

    expressions of customer feedback and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceton
    -0.57
    subtle
    -0.55
    BagConstraints
    -0.51
     Barbier
    -0.50
     Aron
    -0.50
    ROIT
    -0.49
    ÉD
    -0.49
    PHONY
    -0.48
     hod
    -0.48
    ITICAL
    -0.48
    POSITIVE LOGITS
    
    0.70
    aarrggbb
    0.65
     Normdatei
    0.60
     дописавши
    0.60
     ifade
    0.58
    inSlope
    0.57
     bonté
    0.56
    NameInMap
    0.56
     casó
    0.55
     tjen
    0.54
    Act Density 0.176%

    No Known Activations