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

    Neuronpedia

    INDEX
    Explanations

    terms related to user experiences and improvements in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onAttach
    -0.57
    makeConstraints
    -0.53
    めでとう
    -0.47
     rootReducer
    -0.46
     Foote
    -0.44
     שוליים
    -0.44
    BASELINE
    -0.42
     Unicode
    -0.42
    QtCore
    -0.42
     numerus
    -0.42
    POSITIVE LOGITS
     experience
    3.79
    experience
    3.23
     Experience
    3.10
     experiences
    3.08
    Experience
    3.03
     EXPERIENCE
    3.02
     expérience
    2.82
     experiencia
    2.67
    experiences
    2.65
    EXPERIENCE
    2.61
    Act Density 0.412%

    No Known Activations