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

    Neuronpedia

    INDEX
    Explanations

    medical and legal terms related to serious conditions, treatments, and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.79
     is
    -0.63
     are
    -0.60
     Go
    -0.57
     “
    -0.57
     in
    -0.56
     only
    -0.55
     has
    -0.53
     hold
    -0.53
     mer
    -0.53
    POSITIVE LOGITS
     itſelf
    1.11
     pleaſure
    1.03
     myſelf
    1.02
     purpoſe
    1.00
     Houſe
    0.98
     Majefty
    0.93
     houſe
    0.92
    ſelf
    0.92
     ſtate
    0.92
     ſte
    0.90
    Act Density 1.182%

    No Known Activations