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

    Neuronpedia

    INDEX
    Explanations

    dates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "on" followed by a day of the week or specific time-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¦ãĤ¹
    -0.77
    ãĤ´ãĥ³
    -0.69
    Probably
    -0.69
    arily
    -0.68
    atio
    -0.66
    arah
    -0.65
    anuts
    -0.63
    vec
    -0.63
    FIX
    -0.62
    Topic
    -0.62
    POSITIVE LOGITS
     however
    0.98
     meanwhile
    0.78
     citing
    0.72
     announcing
    0.72
     Wikileaks
    0.68
     though
    0.67
     Deadline
    0.66
     amid
    0.65
     HuffPost
    0.65
    lished
    0.64
    Act Density 0.139%

    No Known Activations