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

    Neuronpedia

    INDEX
    Explanations

    quantifiable metrics relating to measurements and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ias
    -0.15
     Sho
    -0.15
     el
    -0.14
    izzy
    -0.14
     bidi
    -0.14
     Stores
    -0.14
    apsed
    -0.14
    tram
    -0.13
     Hyp
    -0.13
     Vs
    -0.13
    POSITIVE LOGITS
    allah
    0.16
     dưỡng
    0.15
    wahl
    0.15
    ajes
    0.14
    mlink
    0.14
    peare
    0.14
    pawn
    0.14
    ãĥ¼ãĤ¹
    0.14
    grave
    0.14
    HIP
    0.14
    Act Density 1.182%

    No Known Activations