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

    Neuronpedia

    INDEX
    Explanations

    expressions of hope and helpfulness in written communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fleet
    -0.17
    vig
    -0.16
     digest
    -0.15
    æĿ
    -0.15
    ä¹İ
    -0.14
     almost
    -0.14
     bÄĥng
    -0.13
     Franco
    -0.13
    hift
    -0.13
    енко
    -0.13
    POSITIVE LOGITS
    entin
    0.17
    sse
    0.15
    886
    0.15
    ontent
    0.15
    undi
    0.14
    polator
    0.14
    ilden
    0.14
    okane
    0.14
    ovÄĽ
    0.14
    ç¸
    0.14
    Act Density 0.063%

    No Known Activations