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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an introduction or transition in a discussion or narrative

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

    following "an," "a," or "some"

    np_acts-logits-general · gemini-2.0-flash

    On a side

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.86
    ftagPool
    -0.75
    MigrationBuilder
    -0.69
    ########.
    -0.66
     nahilalakip
    -0.66
    lamic
    -0.64
    IContainer
    -0.62
     Roskov
    -0.61
    SOUNDBITE
    -0.60
     autorytatywna
    -0.59
    POSITIVE LOGITS
     note
    1.65
    note
    1.30
     Note
    1.28
    Note
    1.19
     caveat
    1.19
     notes
    1.17
     NOTE
    1.14
    NOTE
    1.09
    余談
    1.07
     siden
    1.07
    Act Density 0.293%

    No Known Activations