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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical or scientific conditions and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelves
    -1.12
     itſelf
    -1.03
     pleaſure
    -1.01
     Jefus
    -1.00
     houſe
    -1.00
    ſelf
    -0.99
     themſelves
    -0.98
     Efq
    -0.97
     myſelf
    -0.96
     whoſe
    -0.95
    POSITIVE LOGITS
    ,
    0.55
     pan
    0.55
     the
    0.55
     of
    0.55
     to
    0.53
     "
    0.52
     $
    0.50
     
    0.49
     being
    0.48
     any
    0.48
    Act Density 1.373%

    No Known Activations