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

    Neuronpedia

    INDEX
    Explanations

    negative contractions related to existence or presence

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

    Contractions with n't

    np_acts-logits-general · gemini-2.0-flash

    negative contractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.83
     PACE
    -0.82
    ?>">
    -0.82
    tır
    -0.80
     Thales
    -0.79
     nedenle
    -0.76
     bílá
    -0.75
     IRIS
    -0.75
     Савезне
    -0.75
    Geplaatst
    -0.74
    POSITIVE LOGITS
     isn
    1.05
     shouldn
    1.00
     couldn
    0.96
     wasn
    0.96
     didn
    0.96
     aren
    0.95
     doesn
    0.92
     don
    0.92
     hasn
    0.91
     hadn
    0.90
    Act Density 0.079%

    No Known Activations