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

    Neuronpedia

    INDEX
    Explanations

    mentions of technological or programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jefus
    -1.05
     Majefty
    -1.02
     myſelf
    -0.93
     themſelves
    -0.93
     itſelf
    -0.91
     himſelf
    -0.90
     '\\;'
    -0.90
     Efq
    -0.90
     Houſe
    -0.86
    ſelf
    -0.85
    POSITIVE LOGITS
     to
    0.50
     its
    0.46
     cur
    0.46
     set
    0.46
     t
    0.45
     everything
    0.43
     vz
    0.43
     immediately
    0.43
     things
    0.43
     Bon
    0.43
    Act Density 0.666%

    No Known Activations