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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs indicating an action is about to happen

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their association with actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     discrep
    -0.75
    Offline
    -0.70
    eret
    -0.67
    NOT
    -0.65
    <?
    -0.63
     largeDownload
    -0.63
     preservation
    -0.60
    ãĤ¤ãĥĪ
    -0.60
    north
    -0.60
     avoiding
    -0.59
    POSITIVE LOGITS
     ever
    0.99
     reaches
    0.85
     even
    0.85
     embarked
    0.84
    xit
    0.83
     begins
    0.82
     began
    0.81
     officially
    0.80
     commenced
    0.79
     expires
    0.79
    Act Density 0.112%

    No Known Activations