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

    Neuronpedia

    INDEX
    Explanations

    conjunctions that connect phrases or clauses, specifically forms of "and" and "but"

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    marle
    -0.64
    anglès
    -0.63
     Rek
    -0.62
     $_"
    -0.61
    _'.$
    -0.61
     naturais
    -0.61
     stads
    -0.61
     Theſe
    -0.60
     improvement
    -0.58
    };*/
    -0.57
    POSITIVE LOGITS
    BagConstraints
    0.74
    BufferException
    0.68
    fully
    0.66
    ically
    0.62
    BagLayout
    0.61
     adverbs
    0.61
    illig
    0.60
    ently
    0.60
    Diweddarwch
    0.60
    tagHelperRunner
    0.57
    Act Density 0.020%

    No Known Activations