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

    Neuronpedia

    INDEX
    Explanations

    questions and topics related to individuals' identities and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ब्रेकडाउन
    -0.43
    ]")]
    -0.39
    Portail
    -0.39
     שוליים
    -0.38
     snippetHide
    -0.36
    abestanden
    -0.35
     nového
    -0.34
    ConstraintMaker
    -0.34
     volume
    -0.33
     glitch
    -0.33
    POSITIVE LOGITS
     professionals
    0.66
     instructor
    0.63
     professionisti
    0.62
     ammat
    0.59
     instructors
    0.59
     Instructors
    0.58
     Instructor
    0.58
     Professionals
    0.57
    NameInMap
    0.57
     Scientist
    0.56
    Act Density 0.920%

    No Known Activations