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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the number 28 and its various formats, indicating a focus on dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lier
    -0.17
    canf
    -0.17
    iy
    -0.16
    liest
    -0.15
    chin
    -0.15
    pile
    -0.15
     ÑĤака
    -0.15
    sel
    -0.15
    comings
    -0.15
    ilater
    -0.15
    POSITIVE LOGITS
    one
    0.17
    ifornia
    0.17
    /OR
    0.17
    /bus
    0.16
    alysis
    0.15
    esium
    0.15
    sters
    0.15
    ATEST
    0.15
    ala
    0.15
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.15
    Act Density 0.180%

    No Known Activations