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

    Neuronpedia

    INDEX
    Explanations

    references to basic concepts or terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -1.33
     myſelf
    -1.25
     ſta
    -1.24
     ſche
    -1.24
     houſe
    -1.19
     ſtate
    -1.18
     pleaſure
    -1.17
     iſt
    -1.16
     Eſ
    -1.15
     whoſe
    -1.15
    POSITIVE LOGITS
    ,
    0.78
     
    0.75
     basic
    0.72
     Basic
    0.69
     classic
    0.68
     traditional
    0.67
    ::
    0.67
     (
    0.63
    .
    0.62
    ®
    0.61
    Act Density 0.163%

    No Known Activations