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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and punctuation-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BIN
    -0.16
    926
    -0.16
    ctrine
    -0.16
    oze
    -0.14
    910
    -0.14
    801
    -0.14
    alat
    -0.14
    andom
    -0.14
    åĿĬ
    -0.14
    Ø·ÙĦ
    -0.14
    POSITIVE LOGITS
    ollow
    0.18
    uno
    0.17
    Ìĥ
    0.16
    ariat
    0.15
     betrayed
    0.14
    inkel
    0.14
    umhur
    0.14
    doors
    0.14
     Bett
    0.14
     benches
    0.14
    Act Density 0.000%

    No Known Activations