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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and other connecting words that emphasize relationships in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.05
    3:0.05
    4:0.05
    5:0.04
    6:0.36
    7:0.04
    8:0.03
    9:0.03
    10:0.16
    11:0.09
    Negative Logits
     Telephone
    -1.32
     indemn
    -1.25
    ��
    -1.24
     Township
    -1.22
     estates
    -1.19
     township
    -1.19
     Meadow
    -1.18
     Nationwide
    -1.18
    shire
    -1.16
     Horizons
    -1.16
    POSITIVE LOGITS
    itiveness
    1.53
    terness
    1.47
    redo
    1.45
    ronic
    1.38
    escal
    1.31
     gratification
    1.29
     flavor
    1.29
     vibration
    1.27
    bite
    1.26
    ucker
    1.25
    Act Density 0.001%

    No Known Activations