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

    Neuronpedia

    INDEX
    Explanations

    concepts related to universality and common themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pyx
    -0.77
    ciech
    -0.68
     setPassword
    -0.63
    eradish
    -0.57
     PYTHON
    -0.56
    scss
    -0.56
     productivo
    -0.55
    簿
    -0.54
    achts
    -0.54
    azón
    -0.54
    POSITIVE LOGITS
     universal
    1.94
     universelle
    1.86
    universal
    1.84
     Universal
    1.83
    Universal
    1.80
     UNIVERSAL
    1.79
     universale
    1.74
     universally
    1.60
     universality
    1.53
     universel
    1.49
    Act Density 0.156%

    No Known Activations