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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements of weight and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     big
    -0.51
     temprana
    -0.49
    大型
    -0.47
     conmigo
    -0.46
    literals
    -0.44
     mukana
    -0.43
    tovers
    -0.43
     μεγά
    -0.42
    digheid
    -0.42
    nościo
    -0.41
    POSITIVE LOGITS
    setVerticalGroup
    0.86
     незавершена
    0.79
     average
    0.75
     avg
    0.75
     ſtate
    0.74
     itſelf
    0.74
     mean
    0.74
    LabelTagHelper
    0.73
     themſelves
    0.72
    Xna
    0.72
    Act Density 0.727%

    No Known Activations