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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate authority or expertise, particularly those accompanied by titles, roles, or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jensen
    -0.17
    üp
    -0.16
    auga
    -0.15
    iet
    -0.14
    ?page
    -0.14
    stvÃŃ
    -0.14
    iert
    -0.13
    irts
    -0.13
    abelle
    -0.13
    ebb
    -0.13
    POSITIVE LOGITS
    ató
    0.15
    achinery
    0.15
     Göz
    0.14
    ruh
    0.14
    <small
    0.14
    á»Ļi
    0.14
    opal
    0.13
    .Generated
    0.13
     Conditioning
    0.13
    relay
    0.13
    Act Density 0.101%

    No Known Activations