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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases that highlight preferences or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onic
    -0.51
    2
    -0.50
    B
    -0.49
     lí
    -0.49
    X
    -0.49
    onia
    -0.48
    L
    -0.48
    y
    -0.45
    A
    -0.45
    ish
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    1.13
     للمعارف
    1.09
    IntoConstraints
    1.04
     فريبيس
    0.99
     كومونز
    0.97
     дописавши
    0.95
    setVerticalGroup
    0.94
     betweenstory
    0.94
    MessageOf
    0.94
    AndEndTag
    0.91
    Act Density 0.253%

    No Known Activations