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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and places, along with specific numerical values or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĩик
    -0.16
     P
    -0.16
     Norman
    -0.14
     Tos
    -0.14
     cous
    -0.13
     dat
    -0.13
     Nou
    -0.13
     Michaels
    -0.13
     reli
    -0.13
     Ekon
    -0.13
    POSITIVE LOGITS
    -g
    0.16
    olest
    0.15
    gart
    0.15
    g
    0.15
    ubes
    0.15
    ãĥ¬ãĥĥãĥĪ
    0.15
    iesen
    0.15
    ibri
    0.15
    arf
    0.15
    ãĥ³ãĤ¿
    0.15
    Act Density 0.024%

    No Known Activations