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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uras
    -0.16
    alian
    -0.16
    пеÑĩ
    -0.15
    olv
    -0.15
    rror
    -0.15
    ÑĸÑĪ
    -0.15
    recision
    -0.14
    uddy
    -0.14
    ROID
    -0.14
    minster
    -0.13
    POSITIVE LOGITS
    adele
    0.17
    irk
    0.16
    ाà¤ģ
    0.15
    IGH
    0.15
    duk
    0.14
     relating
    0.14
    aina
    0.14
    colo
    0.13
    YC
    0.13
    翼
    0.13
    Act Density 0.006%

    No Known Activations