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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estre
    -0.17
    uyết
    -0.16
    ndo
    -0.15
    xon
    -0.15
     Hed
    -0.15
     artic
    -0.15
    ensex
    -0.15
    sut
    -0.15
    xbb
    -0.14
    isu
    -0.14
    POSITIVE LOGITS
    eta
    0.16
    dd
    0.14
     度
    0.14
    ograd
    0.14
    ETA
    0.13
    meta
    0.13
     Chester
    0.13
    ple
    0.13
    um
    0.13
     META
    0.13
    Act Density 0.023%

    No Known Activations