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

    Neuronpedia

    INDEX
    Explanations

    negation phrases and qualifiers that emphasize contrasts or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venience
    -0.15
    kal
    -0.15
    inate
    -0.14
     tamp
    -0.14
    dra
    -0.14
    Īëĭ¤
    -0.14
    akin
    -0.14
    fav
    -0.14
    trinsic
    -0.14
    ality
    -0.13
    POSITIVE LOGITS
     only
    0.17
    los
    0.17
    rab
    0.16
    venta
    0.15
    icina
    0.15
    _bitmap
    0.14
     Garner
    0.14
    wor
    0.14
    erras
    0.14
    abler
    0.14
    Act Density 0.031%

    No Known Activations