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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote unprecedented or unique events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asper
    -0.18
    omp
    -0.15
    zell
    -0.15
    iner
    -0.15
    ijken
    -0.15
    wal
    -0.14
     mut
    -0.14
    екÑĤи
    -0.14
    /cop
    -0.14
    arta
    -0.14
    POSITIVE LOGITS
    .RunWith
    0.15
    ÐļТ
    0.15
    -ignore
    0.14
    GN
    0.14
    mary
    0.14
    650
    0.14
    686
    0.14
    654
    0.13
    685
    0.13
    childNodes
    0.13
    Act Density 0.007%

    No Known Activations