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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns across the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     the
    -1.11
     those
    -0.93
     its
    -0.92
     CreateTagHelper
    -0.87
     itself
    -0.84
     their
    -0.82
    the
    -0.82
    tagHelperRunner
    -0.82
    AddTagHelper
    -0.81
     a
    -0.79
    POSITIVE LOGITS
     own
    1.97
     respective
    1.04
     latest
    1.02
     newest
    1.01
     usual
    0.98
     entire
    0.94
    own
    0.90
     Own
    0.89
     propios
    0.87
     propio
    0.87
    Act Density 0.688%

    No Known Activations