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

    Neuronpedia

    INDEX
    Explanations

    references to press releases and media announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arak
    -0.15
    ัวร
    -0.15
    Ùģات
    -0.15
     nat
    -0.14
     пода
    -0.14
     MAG
    -0.14
    984
    -0.14
    elin
    -0.14
    lop
    -0.13
     pod
    -0.13
    POSITIVE LOGITS
    PPP
    0.17
     Patri
    0.15
     Rider
    0.14
    riding
    0.14
    umsuz
    0.14
    swire
    0.14
     Lal
    0.14
    PARATOR
    0.14
     patriarch
    0.13
    zap
    0.13
    Act Density 0.008%

    No Known Activations