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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" in various contexts

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

    turns out to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    expandindo
    -0.41
    __":
    -0.33
     lyrical
    -0.32
    OrEmpty
    -0.32
    __":
    -0.31
     Sodom
    -0.30
     getC
    -0.29
     getM
    -0.29
     delas
    -0.28
    læ
    -0.28
    POSITIVE LOGITS
    <bos>
    0.72
    httphttps
    0.67
     EconPapers
    0.66
     initComponents
    0.64
     wireType
    0.61
    styleType
    0.59
     iNdEx
    0.57
    帖最后由
    0.55
    AnchorStyles
    0.55
    oredCriteria
    0.54
    Act Density 0.309%

    No Known Activations