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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with a period followed by a high activation value, potentially indicating the end of a statement or thought

    oai_token-act-pair · gpt-3.5-turbo

    the presence of sentences that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "$:/
    -0.60
    irlf
    -0.60
    izont
    -0.57
    itially
    -0.56
    escription
    -0.55
    ogun
    -0.54
    ividual
    -0.53
    uese
    -0.52
    uilt
    -0.50
    udicrous
    -0.50
    POSITIVE LOGITS
    .
    1.55
    .(
    1.10
    .</
    1.06
    .*
    1.05
    .]
    1.02
    !.
    1.00
    .<
    1.00
    .:
    0.98
    ._
    0.95
    .[
    0.94
    Act Density 1.433%

    No Known Activations