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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a strong and conclusive statement

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation marks and associated context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cellar
    -0.73
    akia
    -0.69
    izoph
    -0.64
     presidency
    -0.59
     zone
    -0.59
     grip
    -0.58
    onite
    -0.58
     franc
    -0.57
    plet
    -0.57
     unspecified
    -0.56
    POSITIVE LOGITS
     However
    1.20
     Often
    1.07
     Unfortunately
    1.05
     Examples
    1.05
     But
    1.01
     Typically
    1.01
     Occasionally
    0.98
     Recently
    0.97
     Indeed
    0.93
    However
    0.92
    Act Density 0.585%

    No Known Activations