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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating essential or recommended items, actions, or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xil
    -0.50
    WithFormat
    -0.50
    PyExc
    -0.46
    )="
    -0.46
     Halen
    -0.45
     sever
    -0.44
    tslib
    -0.44
    richt
    -0.43
    جم
    -0.41
    Prompt
    -0.41
    POSITIVE LOGITS
     classics
    1.13
     favorites
    1.09
     favourites
    1.07
     pleaſure
    1.01
     faſt
    1.00
     bestseller
    0.98
     favourite
    0.98
     staples
    0.97
     staple
    0.96
     indispensable
    0.96
    Act Density 0.157%

    No Known Activations