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

    Neuronpedia

    INDEX
    Explanations

    instances of lists or sequences, especially those punctuated by commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indeed
    -0.17
    s
    -0.15
     thus
    -0.13
    åıĬåħ¶
    -0.13
    /or
    -0.13
     Indeed
    -0.13
    oba
    -0.13
    -loaded
    -0.13
    259
    -0.13
     böylece
    -0.13
    POSITIVE LOGITS
    iffies
    0.15
    cken
    0.15
    lsru
    0.14
    óng
    0.14
     ÑĢаза
    0.14
    ftware
    0.14
     (?)
    0.13
    bsites
    0.13
    ordes
    0.13
     ÙħÛĮÙĦادÛĮ
    0.13
    Act Density 0.145%

    No Known Activations