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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating rephrasing or restatement of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalTable
    -0.84
     незавершена
    -0.81
     nakalista
    -0.79
    --]
    -0.77
    SourceChecksum
    -0.76
     EconPapers
    -0.73
     ―――――
    -0.72
     cdti
    -0.70
    []);
    -0.66
    addPreferredGap
    -0.66
    POSITIVE LOGITS
    つまり
    0.77
     means
    0.77
    也就是说
    0.74
    즉
    0.71
     meaning
    0.69
    aka
    0.65
     nghĩa
    0.65
    acor
    0.62
     tức
    0.61
     یعنی
    0.61
    Act Density 0.258%

    No Known Activations