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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their associated subjects in sentences

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

    il followed by verb or pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plancher
    -0.42
     hvid
    -0.41
     vœ
    -0.41
     chêne
    -0.40
    Ouest
    -0.40
    ंदु
    -0.40
    fæ
    -0.37
     Ouest
    -0.37
     miroir
    -0.36
     sourire
    -0.36
    POSITIVE LOGITS
     It
    0.82
     it
    0.80
     they
    0.79
    It
    0.76
    they
    0.75
     there
    0.75
    They
    0.75
    THEY
    0.71
     They
    0.68
    There
    0.67
    Act Density 0.005%

    No Known Activations