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

    Neuronpedia

    INDEX
    Explanations

    instances of unexpected events and discoveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Zem
    -0.07
    Tube
    -0.07
    XL
    -0.07
    anz
    -0.07
     ÙĨظر
    -0.07
    allo
    -0.06
    Fatal
    -0.06
    даеÑĤÑģÑı
    -0.06
    жи
    -0.06
     Spicer
    -0.06
    POSITIVE LOGITS
     Patch
    0.07
     blank
    0.06
     a
    0.06
    gow
    0.06
     bol
    0.06
     reb
    0.06
     foot
    0.06
     patch
    0.06
    akis
    0.06
    pack
    0.06
    Act Density 0.007%

    No Known Activations