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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate limitations or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     credi
    -0.43
     VIAF
    -0.43
     errno
    -0.43
     indeed
    -0.40
     pylint
    -0.40
     clearly
    -0.40
     endTime
    -0.39
    Références
    -0.39
     autom
    -0.38
     OAuth
    -0.38
    POSITIVE LOGITS
    setVerticalGroup
    0.74
     merely
    0.68
     лишь
    0.67
    Hanya
    0.66
    แค่
    0.65
     jedynie
    0.63
     mere
    0.63
     sadece
    0.62
     Apenas
    0.62
     yalnızca
    0.61
    Act Density 0.483%

    No Known Activations