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

    Neuronpedia

    INDEX
    Explanations

    expressions of alternatives or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÏĨοÏģ
    -0.16
    ritch
    -0.15
    ovaly
    -0.15
    ulle
    -0.14
    ritz
    -0.14
    ROOT
    -0.14
    etin
    -0.14
    eful
    -0.14
     Vehicles
    -0.14
     Ferry
    -0.14
    POSITIVE LOGITS
    umas
    0.17
    nds
    0.16
     close
    0.15
    ãĥªãĥ¼ãĤº
    0.15
    etre
    0.14
    odo
    0.14
     Swagger
    0.14
    issan
    0.14
    adi
    0.14
    \Bundle
    0.14
    Act Density 0.014%

    No Known Activations