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

    Neuronpedia

    INDEX
    Explanations

    references to configuration settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.60
    hesus
    -0.58
    featureID
    -0.54
    aarrggbb
    -0.53
    makeConstraints
    -0.51
     half
    -0.49
    addMouseListener
    -0.48
     nonUne
    -0.48
    evos
    -0.47
     Half
    -0.47
    POSITIVE LOGITS
    urator
    1.11
    urazione
    0.84
    urate
    0.83
    uation
    0.78
    urable
    0.77
    ures
    0.76
    ration
    0.76
    ured
    0.75
    uración
    0.70
    urati
    0.68
    Act Density 0.147%

    No Known Activations