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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.19
    1:0.02
    2:0.02
    3:0.07
    4:0.03
    5:0.13
    6:0.05
    7:0.01
    8:0.29
    9:0.13
    10:0.01
    11:0.01
    Negative Logits
     Flavoring
    -1.95
     ceremonies
    -1.91
     unanim
    -1.88
    ��
    -1.74
     archaeologists
    -1.61
     Medals
    -1.60
     Parables
    -1.60
     Gleaming
    -1.57
     bonuses
    -1.56
     Tests
    -1.54
    POSITIVE LOGITS
    biz
    2.06
    email
    1.73
    remlin
    1.71
    911
    1.65
    adena
    1.64
    serial
    1.64
    desktop
    1.62
    sylv
    1.61
    christ
    1.61
    arre
    1.61
    Act Density 0.001%

    No Known Activations