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

    Neuronpedia

    INDEX
    Explanations

    historical references and significant time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uggle
    -0.18
    ết
    -0.17
    tainment
    -0.16
    ilion
    -0.15
    stairs
    -0.15
    zcze
    -0.14
    angered
    -0.14
    /lists
    -0.14
    244
    -0.14
     beden
    -0.14
    POSITIVE LOGITS
     sixth
    0.35
     ninth
    0.34
     seventh
    0.34
     fifth
    0.33
     eighth
    0.30
     tenth
    0.29
     fourth
    0.28
     اÙĦÙĤرÙĨ
    0.23
     ele
    0.23
    第
    0.22
    Act Density 0.113%

    No Known Activations