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

    Neuronpedia

    INDEX
    Explanations

    the beginning and end of structured data or code segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     un
    -0.83
     so
    -0.81
     ha
    -0.79
     con
    -0.79
     in
    -0.77
     of
    -0.74
     it
    -0.74
     super
    -0.73
     pro
    -0.73
    ,
    -0.73
    POSITIVE LOGITS
     myſelf
    1.40
     Jefus
    1.38
     himſelf
    1.33
    ſelves
    1.32
    ſelf
    1.29
     itſelf
    1.27
     Anſ
    1.27
     Eſ
    1.26
     Houſe
    1.26
     Efq
    1.25
    Act Density 0.100%

    No Known Activations