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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.56
     Obrador
    -0.55
    Datuak
    -0.55
    LabelTagHelper
    -0.53
    __(/*!
    -0.53
     חיצוניים
    -0.49
    $_['
    -0.49
    raszam
    -0.48
    hésitez
    -0.48
    сылкі
    -0.48
    POSITIVE LOGITS
     note
    1.47
     remember
    1.14
    note
    1.11
     noting
    1.08
     Note
    1.05
     noted
    1.03
     bear
    1.02
     stress
    1.00
     emphasize
    0.99
     noter
    0.99
    Act Density 0.421%

    No Known Activations