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

    Neuronpedia

    INDEX
    Explanations

    markers indicating the beginning of a new section or paragraph in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.74
     purpoſe
    -1.68
     itſelf
    -1.66
     Monfieur
    -1.61
     themſelves
    -1.61
     Jefus
    -1.60
     Majefty
    -1.55
     pleaſure
    -1.55
     houſe
    -1.53
     Houſe
    -1.52
    POSITIVE LOGITS
     
    0.96
    .
    0.82
     "
    0.76
     G
    0.74
     n
    0.72
     e
    0.71
     F
    0.71
     a
    0.71
     (
    0.70
     A
    0.69
    Act Density 0.246%

    No Known Activations