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

    Neuronpedia

    INDEX
    Explanations

    instances of whitespace or line breaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ()))
    -0.60
     helst
    -0.54
    }")
    -0.54
     BorderRadius
    -0.53
    ");
    -0.52
     AdapterView
    -0.52
    "))
    -0.52
    ++)
    -0.51
     MainAxisSize
    -0.51
     hiburan
    -0.50
    POSITIVE LOGITS
    wpi
    0.71
    Бахар
    0.67
    riwal
    0.66
     calendriers
    0.64
    Santis
    0.60
    complexContent
    0.60
    dafx
    0.59
    RepeatedField
    0.58
     propOrder
    0.56
      
    0.56
    Act Density 0.160%

    No Known Activations