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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "noticed" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "noticed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quer
    -0.78
    iche
    -0.74
    venge
    -0.74
    escape
    -0.72
    wives
    -0.70
    ende
    -0.70
    via
    -0.69
    quote
    -0.69
    ggies
    -0.65
    heed
    -0.65
    POSITIVE LOGITS
     noticed
    0.80
     notice
    0.77
     notices
    0.77
     Notice
    0.74
     Signs
    0.72
    Notice
    0.70
     Gained
    0.70
    arthed
    0.69
     Slug
    0.69
     Leilan
    0.68
    Act Density 0.012%

    No Known Activations