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

    Neuronpedia

    INDEX
    Explanations

    instances of special characters and certain punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĻeh
    -0.17
    ланд
    -0.17
    APPER
    -0.16
    lander
    -0.15
    hol
    -0.15
    895
    -0.15
    anco
    -0.15
     pÅĻÃŃ
    -0.15
    å¯Ħ
    -0.15
    hots
    -0.15
    POSITIVE LOGITS
    aru
    0.17
    uers
    0.16
    odi
    0.15
    uff
    0.15
     Pros
    0.15
     tr
    0.15
     ost
    0.14
    ãĥ¼ãĤ¹ãĥĪ
    0.14
    cee
    0.14
    urre
    0.14
    Act Density 0.013%

    No Known Activations