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

    Neuronpedia

    INDEX
    Explanations

    conversational phrases and informal expressions

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

    conjunctions or consequence markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.52
    aing
    -0.44
     INFL
    -0.44
     namen
    -0.44
     inf
    -0.44
     Operator
    -0.43
    աստ
    -0.43
    uevo
    -0.43
     Useful
    -0.42
    SIG
    -0.41
    POSITIVE LOGITS
    才会
    0.44
    我才
    0.44
    出版年
    0.43
    才會
    0.43
    จึง
    0.43
    ถึง
    0.42
     才
    0.41
    才是
    0.40
    해야
    0.40
    才
    0.39
    Act Density 0.055%

    No Known Activations