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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sports, particularly football (NFL) players for home teams or personal stories, as well as terms concerning technological products

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    .?
    -0.82
    .",
    -0.81
    ?",
    -0.75
    âĢ¦..
    -0.69
    estine
    -0.67
    âĢ¦."
    -0.67
    .....
    -0.67
    .,"
    -0.66
    ",
    -0.65
    âĢ¦.
    -0.61
    POSITIVE LOGITS
    ãĥĩãĤ£
    0.62
    ãĥ¥
    0.62
     nods
    0.60
     unwitting
    0.58
     nod
    0.58
     winds
    0.57
    itudinal
    0.56
    ãĥīãĥ©
    0.55
     cue
    0.55
     intervals
    0.54
    Act Density 0.659%

    No Known Activations