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

    Neuronpedia

    INDEX
    Explanations

    contractions of verbs in context

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating self-reference and second-person address

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Site
    -0.74
    Click
    -0.69
    trace
    -0.69
    Tweet
    -0.68
    ð
    -0.67
    LIN
    -0.66
    SP
    -0.65
    IB
    -0.65
    EP
    -0.64
    ãĤ¹ãĥĪ
    -0.64
    POSITIVE LOGITS
     gonna
    0.77
    been
    0.77
    selves
    0.71
     entitled
    0.70
     Been
    0.70
     been
    0.68
     gon
    0.64
     definitely
    0.64
     gotta
    0.62
     likely
    0.62
    Act Density 0.181%

    No Known Activations