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

    Neuronpedia

    INDEX
    Explanations

    specific numerical data or results in scientific publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.20
     itſelf
    -1.09
     themſelves
    -1.08
     Jefus
    -1.03
    ChildScrollView
    -1.01
     pleaſure
    -0.99
     متعلقه
    -0.99
     houſe
    -0.98
     himſelf
    -0.97
     Efq
    -0.95
    POSITIVE LOGITS
     for
    0.49
     '
    0.49
     "
    0.49
    ...
    0.48
     to
    0.47
     £
    0.46
     much
    0.46
    ↵
    0.45
     L
    0.45
    ↵↵
    0.45
    Act Density 0.297%

    No Known Activations