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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific function words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.04
    2:0.06
    3:0.04
    4:0.06
    5:0.05
    6:0.19
    7:0.05
    8:0.08
    9:0.25
    10:0.03
    11:0.04
    Negative Logits
     Hawai
    -4.26
    packing
    -3.95
    aho
    -3.75
    �
    -3.58
     Hawaiian
    -3.56
    pack
    -3.48
     Pilgrim
    -3.38
    hun
    -3.36
    uo
    -3.33
    packs
    -3.32
    POSITIVE LOGITS
     Der
    9.63
    Der
    9.24
     Derby
    8.40
    der
    6.40
     der
    5.85
    DER
    5.08
     Dahl
    5.01
     Dixon
    4.78
     Die
    4.73
    Die
    4.65
    Act Density 0.003%

    No Known Activations