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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitional phrases that suggest continuation or connection in the text

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

    this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GTCX
    -0.48
    phazard
    -0.48
    trg
    -0.47
     tramonto
    -0.45
     frequenza
    -0.45
     mahd
    -0.45
     bandeira
    -0.44
     amostra
    -0.44
    verns
    -0.44
    anceled
    -0.44
    POSITIVE LOGITS
     disponibilités
    0.46
     something
    0.41
     thing
    0.41
     Вікі
    0.39
     Pingback
    0.37
     rzecz
    0.35
     stuff
    0.35
     somethin
    0.35
    Malaysia
    0.35
    Pranala
    0.35
    Act Density 0.060%

    No Known Activations