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

    Neuronpedia

    INDEX
    Explanations

    keywords related to user instructions, software installation, and technical operations

    oai_token-act-pair · gpt-3.5-turbo

    second-person pronouns and related phrases addressing the reader directly

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.66
    ¿½
    -0.65
    quarters
    -0.62
     Excellence
    -0.61
    åħī
    -0.61
    ĸļ
    -0.60
    adium
    -0.60
    polit
    -0.59
    ivism
    -0.59
     modesty
    -0.58
    POSITIVE LOGITS
    'll
    1.34
     can
    1.25
    're
    1.04
     should
    1.03
     may
    1.01
     specify
    0.99
     need
    0.99
     configure
    0.99
     will
    0.98
     MUST
    0.98
    Act Density 0.089%

    No Known Activations