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

    Neuronpedia

    INDEX
    Explanations

    terms related to leadership, business potential, and the consequences of choice

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

    Preceding comma followed by adversative conjunction

    np_acts-logits-general · gemini-2.0-flash

    not... but.

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pourtant
    -1.09
    Yet
    -1.03
     Yet
    -1.01
     pourtant
    -0.93
     entanto
    -0.91
     yet
    -0.90
     cependant
    -0.82
    yet
    -0.80
     néanmoins
    -0.80
     However
    -0.77
    POSITIVE LOGITS
     sondern
    1.43
     sino
    1.23
     אלא
    1.18
     بلکه
    1.17
     hanem
    1.16
    而是
    1.09
     utan
    1.09
     vaan
    1.04
     melainkan
    0.98
     mà
    0.89
    Act Density 0.178%

    No Known Activations