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

    Neuronpedia

    INDEX
    Explanations

    negative or critical sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ex- titles and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -1.23
    ロウィン
    -1.22
    <unused42>
    -1.18
    <unused43>
    -1.18
    <unused28>
    -1.18
    <unused8>
    -1.18
    <unused14>
    -1.17
    <unused16>
    -1.17
    <unused3>
    -1.17
    [@BOS@]
    -1.17
    POSITIVE LOGITS
     former
    0.86
    Former
    0.81
     Former
    0.77
     ex
    0.67
    former
    0.54
    ex
    0.54
     ehemalige
    0.53
     eski
    0.46
    Ex
    0.45
     mantan
    0.44
    Act Density 0.003%

    No Known Activations