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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to classifiers and feature selection methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.63
     nonatomic
    -0.60
     Ache
    -0.60
    oredCriteria
    -0.58
     estri
    -0.57
     themſelves
    -0.57
     pleaſure
    -0.57
    χρι
    -0.57
    Cous
    -0.56
     Etr
    -0.56
    POSITIVE LOGITS
    PerformLayout
    0.86
     متعلقه
    0.81
     surla
    0.76
    الحياه
    0.66
    thâu
    0.65
    expandindo
    0.61
     TestBed
    0.60
     незавершена
    0.59
    makeConstraints
    0.57
     >=",
    0.56
    Act Density 0.161%

    No Known Activations