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

    Neuronpedia

    INDEX
    Explanations

    specific names of cities and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ethiopian
    -0.16
     Ethiopia
    -0.14
    PHA
    -0.14
    acid
    -0.14
    urement
    -0.14
    oker
    -0.14
     intrinsic
    -0.14
    Ñĥнд
    -0.14
    sect
    -0.14
    removeAttr
    -0.14
    POSITIVE LOGITS
     Kazakhstan
    0.36
     Kaz
    0.30
     Nur
    0.22
     Nurs
    0.21
    kaz
    0.21
     Ðļаз
    0.20
     Prairie
    0.19
     kaz
    0.18
     каз
    0.18
    bek
    0.17
    Act Density 0.027%

    No Known Activations