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

    Neuronpedia

    INDEX
    Explanations

    headings or titles that introduce sections of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     a
    -1.12
     the
    -1.02
     in
    -0.95
     of
    -0.93
     
    -0.92
     her
    -0.90
     it
    -0.87
     to
    -0.84
     an
    -0.84
     I
    -0.82
    POSITIVE LOGITS
     Anſ
    1.53
     itſelf
    1.52
     Efq
    1.49
     ſche
    1.49
     myſelf
    1.48
     pleaſure
    1.48
     Monfieur
    1.48
     ſtate
    1.47
     purpoſe
    1.44
     Jefus
    1.42
    Act Density 0.636%

    No Known Activations