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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditional relationships or highlight effects and consequences

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

    conjunctions and transition words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ือก
    -0.38
    Vidite
    -0.35
    bkz
    -0.35
    Hentet
    -0.33
    ヴ
    -0.31
    absolute
    -0.31
     selection
    -0.31
    vou
    -0.30
     Sk
    -0.29
     verb
    -0.29
    POSITIVE LOGITS
    MemoryWarning
    0.81
    SharedCtor
    0.69
    setVerticalGroup
    0.68
    StructEnd
    0.68
    TagMode
    0.63
    expandindo
    0.59
    Personendaten
    0.59
     cauza
    0.57
     niestety
    0.57
    matitis
    0.54
    Act Density 0.856%

    No Known Activations