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

    Neuronpedia

    INDEX
    Explanations

    terms related to success and effective outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kett
    -0.74
     propOrder
    -0.67
     depreciation
    -0.62
    onAttach
    -0.62
     reacts
    -0.62
     ecto
    -0.61
     eosin
    -0.60
     shears
    -0.60
    Esk
    -0.60
     Kant
    -0.60
    POSITIVE LOGITS
    Successful
    1.19
     successful
    1.16
     Successful
    1.12
    successful
    1.08
     Powerful
    1.03
    IFUL
    1.00
    Powerful
    0.94
     Beautiful
    0.92
    rateful
    0.92
     successfully
    0.91
    Act Density 0.094%

    No Known Activations