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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and terms related to preferences and choices

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

    followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    those (plural/feminine)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.72
    abetes
    -0.71
    exitRule
    -0.69
     itſelf
    -0.68
     betweenstory
    -0.68
    MigrationBuilder
    -0.66
     themſelves
    -0.64
     oprot
    -0.64
     ExecuteAsync
    -0.63
     Monfieur
    -0.63
    POSITIVE LOGITS
     those
    1.29
     aquellos
    1.11
    those
    1.09
     aquellas
    1.04
    Those
    1.01
     Those
    1.00
     aqueles
    0.99
    那些
    0.89
     những
    0.89
     aquella
    0.84
    Act Density 1.062%

    No Known Activations