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

    Neuronpedia

    INDEX
    Explanations

    instances of personal experiences or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entar
    -0.18
    .Align
    -0.17
    elman
    -0.17
    chwitz
    -0.16
    illin
    -0.15
    istrovstvÃŃ
    -0.15
    frag
    -0.15
    ÑĢаÑĩ
    -0.15
    ιλ
    -0.14
    ALAR
    -0.14
    POSITIVE LOGITS
    osemite
    0.15
     wid
    0.15
     lie
    0.14
     Victims
    0.14
    angu
    0.14
     Mason
    0.14
    ìĨį
    0.14
     Kun
    0.14
    isky
    0.13
     lump
    0.13
    Act Density 0.009%

    No Known Activations