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

    Neuronpedia

    INDEX
    Explanations

    document structure indicators or metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     al
    -0.70
     si
    -0.70
     ki
    -0.69
     if
    -0.68
     do
    -0.67
    ,
    -0.67
     con
    -0.66
     ne
    -0.66
     in
    -0.66
     mu
    -0.66
    POSITIVE LOGITS
     itſelf
    1.27
     myſelf
    1.20
     Anſ
    1.19
     himſelf
    1.16
     Jefus
    1.15
    ſelves
    1.15
     Houſe
    1.11
     Eſ
    1.06
     themſelves
    1.06
     Efq
    1.06
    Act Density 0.344%

    No Known Activations