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

    Neuronpedia

    INDEX
    Explanations

    references to medical studies and clinical evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gra
    -0.58
     and
    -0.58
    ,
    -0.52
     
    -0.52
     ten
    -0.51
     pu
    -0.51
     un
    -0.51
    gi
    -0.51
     low
    -0.50
     pas
    -0.49
    POSITIVE LOGITS
    ſelves
    1.19
    ſelf
    1.18
     Majefty
    1.16
     Houſe
    1.11
     Monfieur
    1.10
     itſelf
    1.06
    tvguidetime
    1.05
    neſs
    1.04
     myſelf
    1.03
     שוליים
    1.01
    Act Density 0.720%

    No Known Activations