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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their significance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    figure labels `![(a)`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.58
    jsii
    -0.51
    ỡng
    -0.50
     Andrews
    -0.48
    клопе
    -0.48
     Shadow
    -0.47
    SW
    -0.47
     Hend
    -0.45
    Shadow
    -0.45
    tagext
    -0.44
    POSITIVE LOGITS
    
    1.87
     [*]
    0.71
    
    0.68
    Personensuche
    0.63
    FieldNumber
    0.57
    
    0.56
    
    0.54
    ########.
    0.53
    
    0.52
    
    0.49
    Act Density 0.000%

    No Known Activations