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

    Neuronpedia

    INDEX
    Explanations

    the definite article "the" and pronouns

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     him
    -0.55
     them
    -0.54
     isso
    -0.53
     Estar
    -0.48
    še
    -0.47
     deles
    -0.47
     RSSSF
    -0.47
    bbene
    -0.46
    ह
    -0.46
     avanti
    -0.45
    POSITIVE LOGITS
    rungsseite
    1.02
     &___
    1.00
     Савезне
    0.88
    WriteBarrier
    0.88
     esternos
    0.86
    webElementXpaths
    0.83
    addCriterion
    0.82
     estekak
    0.82
     autorytatywna
    0.82
    UnknownFieldSet
    0.79
    Act Density 0.033%

    No Known Activations