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

    Neuronpedia

    INDEX
    Explanations

    concepts related to theories and theoretical frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ellan
    -0.17
    áÄį
    -0.17
    itude
    -0.16
    strike
    -0.16
    acre
    -0.15
    ibur
    -0.15
    ante
    -0.15
    سÙĪب
    -0.15
    że
    -0.15
    erals
    -0.15
    POSITIVE LOGITS
    czy
    0.17
    ically
    0.17
    /pr
    0.17
     dõi
    0.15
    rence
    0.15
    ched
    0.15
    çĽĺ
    0.15
    -pr
    0.15
     Tod
    0.15
    ERSHEY
    0.14
    Act Density 0.022%

    No Known Activations