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

    Neuronpedia

    INDEX
    Explanations

    phrases related to needing or searching for a specific person with certain qualities

    oai_token-act-pair · gpt-3.5-turbo

    references to the need for specific people or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utenberg
    -0.67
    ovember
    -0.63
    inth
    -0.62
     culmin
    -0.60
     concludes
    -0.59
    Closure
    -0.56
     incorrectly
    -0.55
     snowball
    -0.55
     Revelations
    -0.54
    Operation
    -0.54
    POSITIVE LOGITS
     willing
    1.41
     whom
    1.17
     who
    1.14
     capable
    1.14
     suitable
    1.08
    who
    1.05
     trustworthy
    1.03
     whose
    0.94
     sympathetic
    0.92
     knowledgeable
    0.91
    Act Density 0.364%

    No Known Activations