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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and phrases indicating relative quantities or changes

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

    Comparison or relative quantity

    np_acts-logits-general · gemini-2.0-flash

    quantitative comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.65
    protoc
    -0.62
     useStyles
    -0.56
    CPtr
    -0.55
    expandindo
    -0.53
     թվական
    -0.52
     useState
    -0.51
     فريبيس
    -0.51
     betweenstory
    -0.51
    igneurs
    -0.50
    POSITIVE LOGITS
     than
    1.42
     compared
    1.40
     compare
    1.18
    compared
    1.01
     comparing
    0.99
     compares
    0.99
     comparison
    0.98
     Compared
    0.93
     Compare
    0.87
     Comparing
    0.87
    Act Density 0.239%

    No Known Activations