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

    Neuronpedia

    INDEX
    Explanations

    the beginning of text segments or paragraphs

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

    We begin, we conclude, we therefore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.92
     فريبيس
    -0.90
    Personendaten
    -0.84
     Efq
    -0.84
    GEBURTSDATUM
    -0.83
    httphttps
    -0.82
    WithIOException
    -0.81
    ,:);
    -0.80
    tagHelperRunner
    -0.80
    addCriterion
    -0.79
    POSITIVE LOGITS
     hope
    0.79
     believe
    0.62
     therefore
    0.61
     Hope
    0.54
    hope
    0.53
     hoping
    0.52
     hopes
    0.52
     hoped
    0.50
     Furthermore
    0.50
     believes
    0.50
    Act Density 0.115%

    No Known Activations