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

    Neuronpedia

    INDEX
    Explanations

    terms related to professionalism in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     numberWith
    -0.69
    pertise
    -0.69
    IndexOutOfBounds
    -0.65
     skry
    -0.63
     evt
    -0.62
     Tind
    -0.62
    łoży
    -0.60
    phorbia
    -0.60
     Kud
    -0.59
    iconductor
    -0.59
    POSITIVE LOGITS
     Profesional
    0.93
    Profession
    0.80
    Profes
    0.78
     unprofessional
    0.78
    PROFESSIONAL
    0.77
     professions
    0.77
    profes
    0.75
    professionals
    0.75
    professional
    0.74
    фессиона
    0.73
    Act Density 0.010%

    No Known Activations