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

    Neuronpedia

    INDEX
    Explanations

    words related to instructions or advice

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'A' used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arsity
    -0.70
     Orient
    -0.65
    olicy
    -0.64
     Everton
    -0.64
    Finish
    -0.62
    aneously
    -0.62
    evidence
    -0.60
    Merit
    -0.59
     proceedings
    -0.59
    apesh
    -0.58
    POSITIVE LOGITS
    cknowled
    1.74
    cknow
    1.51
    verages
    1.24
     lot
    1.03
    chieve
    1.00
    chie
    0.98
     typical
    0.98
     downside
    0.97
     drawback
    0.95
    lyss
    0.94
    Act Density 0.141%

    No Known Activations