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

    Neuronpedia

    INDEX
    Explanations

    repetitive conjunctions in a text

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

    and followed by names or titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfieras
    -0.41
    IUrlHelper
    -0.41
    SequentialGroup
    -0.39
     Himo
    -0.38
    Dữ
    -0.36
    었
    -0.36
    +#+#
    -0.34
     recurrent
    -0.34
    rovnik
    -0.34
     autorytatywna
    -0.33
    POSITIVE LOGITS
    RegressionTest
    0.59
    Personendaten
    0.52
    └──
    0.50
    transQ
    0.49
    StructEnd
    0.48
    AndEndTag
    0.48
     betweenstory
    0.47
     CanadaChoose
    0.47
     bonus
    0.47
    ########.
    0.45
    Act Density 0.002%

    No Known Activations