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

    Neuronpedia

    INDEX
    Explanations

    negative constructions and expressions of limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ynom
    -0.19
    adolu
    -0.15
     Maz
    -0.15
    baseline
    -0.15
     forg
    -0.15
    rotch
    -0.15
    ICODE
    -0.14
    ycastle
    -0.14
    BOVE
    -0.13
    irim
    -0.13
    POSITIVE LOGITS
    izio
    0.18
    ori
    0.18
    ä¸ĢèĪ¬
    0.15
     necessarily
    0.15
    afia
    0.15
    ektor
    0.15
    ÄĽn
    0.14
    lijk
    0.14
    åĿĩ
    0.13
     borders
    0.13
    Act Density 0.241%

    No Known Activations