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

    Neuronpedia

    INDEX
    Explanations

    negative expressions or contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coni
    -0.16
    PFN
    -0.15
    anes
    -0.15
    anca
    -0.14
     Brill
    -0.14
    ifo
    -0.14
    amient
    -0.14
    utut
    -0.14
    .Span
    -0.13
    é½
    -0.13
    POSITIVE LOGITS
    ãĥĥãĥĪ
    0.15
    áÄį
    0.14
    ³
    0.14
    nev
    0.14
    unya
    0.14
    zimmer
    0.14
    彦
    0.14
     nev
    0.14
    анÑĤаж
    0.13
    puts
    0.13
    Act Density 0.021%

    No Known Activations