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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to a person or a group

    oai_token-act-pair · gpt-3.5-turbo

    references to subject pronouns and the implications of actions or states related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTOS
    -0.72
     Gri
    -0.65
     Bore
    -0.62
    UGE
    -0.61
    rawdownloadcloneembedreportprint
    -0.61
     Penny
    -0.58
    ciating
    -0.57
    WATCH
    -0.56
     Notting
    -0.56
    ãĤ·ãĥ£
    -0.56
    POSITIVE LOGITS
    'll
    1.32
     shouldn
    1.16
     surely
    1.16
     would
    1.16
     will
    1.16
     wouldn
    1.15
     might
    1.13
     ought
    1.13
     probably
    1.11
     should
    1.10
    Act Density 0.227%

    No Known Activations