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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal growth and change over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nier
    -0.17
    reon
    -0.17
    ód
    -0.15
    ãĥ¥
    -0.15
    -ÑĤо
    -0.15
    _regs
    -0.14
    ãģ¡ãĤĩãģ£ãģ¨
    -0.14
     somewhere
    -0.14
     something
    -0.14
     cannot
    -0.14
    POSITIVE LOGITS
    undry
    0.16
    ipa
    0.15
    agnostics
    0.15
     باز
    0.14
    ynet
    0.14
    ynn
    0.14
    olo
    0.14
     willing
    0.14
     Hund
    0.14
    ene
    0.14
    Act Density 0.079%

    No Known Activations