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

    Neuronpedia

    INDEX
    Explanations

    references to questions being asked to individuals

    oai_token-act-pair · gpt-3.5-turbo

    the verb "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PsyNetMessage
    -0.83
     Franch
    -0.78
     Compan
    -0.73
     Convert
    -0.72
    izable
    -0.69
     Apply
    -0.68
    ologies
    -0.67
    ulton
    -0.66
     Fail
    -0.65
     Submit
    -0.65
    POSITIVE LOGITS
     briefed
    1.10
     quoted
    1.08
     adamant
    1.07
     visibly
    1.07
     asked
    1.06
     emph
    1.06
     flanked
    1.05
     unequiv
    1.04
     dismissive
    1.03
     interviewed
    1.01
    Act Density 0.172%

    No Known Activations