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

    Neuronpedia

    INDEX
    Explanations

    terms related to regulatory compliance and procedural obligations

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

    Legal or contractual obligations with "shall"

    np_acts-logits-general · gemini-2.0-flash

    shall followed by mandatory verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    many
    -0.67
     many
    -0.63
    atalos
    -0.61
     dozens
    -0.61
    Almost
    -0.61
     nakalista
    -0.61
     yesterday
    -0.60
     Ironically
    -0.59
     nemlig
    -0.59
     MANY
    -0.58
    POSITIVE LOGITS
     wherever
    1.09
     whenever
    1.06
     preferably
    0.99
     shall
    0.97
     Wherever
    0.94
     soweit
    0.93
    Wherever
    0.92
    whenever
    0.91
     Whenever
    0.89
    preferably
    0.87
    Act Density 0.473%

    No Known Activations