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

    Neuronpedia

    INDEX
    Explanations

    strings related to programming and coding, particularly involving characters and data types

    oai_token-act-pair · gpt-3.5-turbo

    programming terminology related to strings and character data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ),"
    -0.75
     Dund
    -0.68
     psychiat
    -0.65
     tatt
    -0.62
    :[
    -0.60
     Urug
    -0.60
    kil
    -0.59
    ."[
    -0.59
    ��
    -0.58
    bleacher
    -0.58
    POSITIVE LOGITS
     >
    2.68
    >
    2.43
    >)
    2.08
    >,
    2.06
    >.
    1.98
    >"
    1.97
     >>
    1.89
    _>
    1.82
     ><
    1.82
    >[
    1.81
    Act Density 0.066%

    No Known Activations