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

    Neuronpedia

    INDEX
    Explanations

    identifiers related to people or characters in news or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹īà¸Ńà¸Ļ
    -0.15
    Ìī
    -0.15
    adelphia
    -0.15
     Citizenship
    -0.14
     globals
    -0.14
    .vector
    -0.14
    èĬĤ
    -0.14
    CLUDING
    -0.14
     scé
    -0.14
    лоп
    -0.13
    POSITIVE LOGITS
    izza
    0.19
     Ber
    0.16
    uisse
    0.16
    lags
    0.16
    coni
    0.15
    ény
    0.15
    evin
    0.15
    istrovstvÃŃ
    0.15
    etest
    0.15
    ειο
    0.15
    Act Density 0.021%

    No Known Activations