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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal identity or self-descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mayer
    -0.15
    zeitig
    -0.15
    empor
    -0.15
    istrovstvÃŃ
    -0.14
    ighton
    -0.14
    -legged
    -0.14
    apore
    -0.14
    ãĤ¤ãĥ«
    -0.14
     automáticamente
    -0.14
     stripe
    -0.13
    POSITIVE LOGITS
    ollo
    0.17
    nj
    0.17
    elin
    0.16
    ÙĬÙĪÙĨ
    0.15
    rians
    0.15
    íĸī
    0.15
     Sabb
    0.15
    uno
    0.15
     bon
    0.15
    elu
    0.15
    Act Density 0.034%

    No Known Activations