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

    Neuronpedia

    INDEX
    Explanations

    expressions related to comparisons and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONTAL
    -0.16
    emy
    -0.15
    istrovstvÃŃ
    -0.15
     getVersion
    -0.15
    InView
    -0.15
    mainwindow
    -0.14
    ÐĿаÑģ
    -0.14
    alace
    -0.14
    sez
    -0.14
    ÇIJ
    -0.14
    POSITIVE LOGITS
     nature
    0.42
     ilk
    0.41
     stripe
    0.39
     persuasion
    0.34
     magnitude
    0.34
    ilk
    0.32
     vintage
    0.32
    nature
    0.32
     stripes
    0.31
     caliber
    0.31
    Act Density 0.076%

    No Known Activations