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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "so" indicating emphasis or conclusion

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

    introduces a consequence or result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.41
    Ethylbenzene
    -0.40
     ویکی‌پدی
    -0.36
     nég
    -0.36
    AxisAlignment
    -0.35
     judiciaire
    -0.35
     térmica
    -0.34
    oflavin
    -0.33
    isContained
    -0.33
    Trichlor
    -0.32
    POSITIVE LOGITS
     therefore
    0.68
    於是
    0.67
    therefore
    0.63
    于是
    0.63
    Therefore
    0.60
     Therefore
    0.59
     hence
    0.55
     Derfor
    0.54
    Поэтому
    0.54
     ezért
    0.53
    Act Density 0.007%

    No Known Activations