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

    Neuronpedia

    INDEX
    Explanations

    instances of inclusion, criteria, and listing related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.16
     myſelf
    -1.06
    AndEndTag
    -1.02
     poffible
    -1.00
     raiſ
    -0.97
     uſed
    -0.94
     ſeveral
    -0.94
     purpoſe
    -0.92
    ſelves
    -0.92
     GenerationType
    -0.90
    POSITIVE LOGITS
    :
    0.83
    toEqual
    0.65
     
    0.62
     include
    0.62
     adalah
    0.59
     is
    0.58
     :
    0.55
     a
    0.55
    的是
    0.51
    的就是
    0.49
    Act Density 0.593%

    No Known Activations