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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific numbers indicating sections or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ymes
    -0.16
    annies
    -0.16
     Walsh
    -0.15
    ẻ
    -0.15
    826
    -0.14
    bsp
    -0.14
    BS
    -0.14
    BA
    -0.14
    AAA
    -0.14
    agate
    -0.14
    POSITIVE LOGITS
    atik
    0.15
     Hir
    0.15
    rowser
    0.14
    paralle
    0.14
     kariy
    0.14
     McCart
    0.14
    gression
    0.14
    oreach
    0.14
    ipp
    0.14
    ffen
    0.13
    Act Density 0.000%

    No Known Activations