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

    Neuronpedia

    INDEX
    Explanations

    phrases and terminology related to statistical effects and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.57
     للاسماء
    -0.54
    ipient
    -0.54
     виправивши
    -0.51
    OCCURRED
    -0.50
     BIBSYS
    -0.49
     GenerationType
    -0.49
     windmill
    -0.49
     cupboards
    -0.48
     cupboard
    -0.48
    POSITIVE LOGITS
     value
    0.50
     values
    0.45
     estimate
    0.41
     ratio
    0.41
     determination
    0.41
     determine
    0.39
     rate
    0.39
     estimated
    0.38
     measured
    0.38
     required
    0.37
    Act Density 0.142%

    No Known Activations