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

    Neuronpedia

    INDEX
    Explanations

    phrases conveying explanations or justifications for actions or situations

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

    because/since clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tedy
    -0.39
     eventdata
    -0.38
    actus
    -0.37
    frem
    -0.35
     entonces
    -0.35
    therefore
    -0.34
     onBackPressed
    -0.34
     therefore
    -0.34
    GIVEREF
    -0.34
    WriteAttribute
    -0.33
    POSITIVE LOGITS
    tagHelperRunner
    0.67
     autorytatywna
    0.58
     nahilalakip
    0.56
     uſed
    0.55
     ſte
    0.53
     gynhyrchwyd
    0.52
     ſtand
    0.52
     Himo
    0.52
    parsedMessage
    0.49
     verſ
    0.49
    Act Density 0.060%

    No Known Activations