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

    Neuronpedia

    INDEX
    Explanations

    dates expressed as month and year

    oai_token-act-pair · gpt-3.5-turbo

    frequent use of commas in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.77
    ãĤ¦ãĤ¹
    -0.74
    arah
    -0.73
    FIX
    -0.69
    ãĥ¥
    -0.69
    Cause
    -0.67
    atio
    -0.67
    alo
    -0.67
    zar
    -0.66
    arily
    -0.66
    POSITIVE LOGITS
     however
    1.05
     meanwhile
    0.90
     when
    0.73
     though
    0.71
     moreover
    0.70
     according
    0.69
    when
    0.69
     citing
    0.66
    lished
    0.65
     although
    0.65
    Act Density 0.171%

    No Known Activations