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

    Neuronpedia

    INDEX
    Explanations

    occurrences of punctuation marks or quotation-related language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    огÑĢад
    -0.17
    abin
    -0.17
     stip
    -0.16
    assin
    -0.15
    172
    -0.15
    imi
    -0.15
    oppel
    -0.14
     swe
    -0.14
     Zw
    -0.14
    aroo
    -0.14
    POSITIVE LOGITS
    iê
    0.18
    olla
    0.16
    ude
    0.16
    OLA
    0.14
    oment
    0.14
    ocl
    0.14
    ìĤ¬
    0.14
    cdc
    0.13
    uppy
    0.13
    oren
    0.13
    Act Density 0.002%

    No Known Activations