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

    Neuronpedia

    INDEX
    Explanations

    structural elements related to data representation, such as nodes and edges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dor
    -0.85
    Dor
    -0.83
     DOR
    -0.83
     Doran
    -0.76
    DOR
    -0.76
     Ak
    -0.75
     Leonard
    -0.73
     LK
    -0.72
     Fleck
    -0.71
    Ak
    -0.71
    POSITIVE LOGITS
     Tony
    1.07
     Blake
    1.00
     Rhonda
    0.99
     ABC
    0.96
    Tony
    0.94
     Bella
    0.87
    Blake
    0.85
    ABC
    0.82
     Rh
    0.80
    Bella
    0.79
    Act Density 1.803%

    No Known Activations