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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.03
    2:0.04
    3:0.05
    4:0.04
    5:0.04
    6:0.11
    7:0.03
    8:0.04
    9:0.49
    10:0.02
    11:0.02
    Negative Logits
    oux
    -4.03
     Barth
    -3.59
     Skydragon
    -3.34
     typew
    -3.25
    zo
    -3.25
     decon
    -3.23
    dayName
    -3.21
     broker
    -3.18
    �
    -3.17
    asters
    -3.11
    POSITIVE LOGITS
    il
    6.56
    IL
    6.32
    ils
    5.70
    iled
    5.02
    iling
    4.98
     Hil
    4.90
    ILS
    4.90
     Il
    4.85
    iles
    4.79
    Gil
    4.79
    Act Density 0.008%

    No Known Activations