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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating relationships or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ìĥ
    -0.16
    laz
    -0.15
    ibel
    -0.15
     Cust
    -0.15
    rij
    -0.15
    lemen
    -0.14
    /generated
    -0.14
    443
    -0.14
     wheel
    -0.14
     Pillow
    -0.14
    POSITIVE LOGITS
    udge
    0.17
    ãĥ³ãĤ¬
    0.17
    UDGE
    0.16
     Shepherd
    0.15
     ext
    0.15
    uzu
    0.15
     floats
    0.15
    leaf
    0.15
     intr
    0.15
    ours
    0.14
    Act Density 0.001%

    No Known Activations