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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating connections or additions in a sentence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.04
    4:0.07
    5:0.02
    6:0.33
    7:0.04
    8:0.04
    9:0.03
    10:0.15
    11:0.11
    Negative Logits
    inventoryQuantity
    -1.87
    gaard
    -1.56
    ゴン
    -1.36
     rooft
    -1.33
    hower
    -1.33
    ック
    -1.31
    ワン
    -1.31
    ��
    -1.28
    ctive
    -1.25
     fault
    -1.22
    POSITIVE LOGITS
    minded
    1.39
    turned
    1.32
     recruits
    1.29
    icipated
    1.24
     recru
    1.24
    ummies
    1.22
     hire
    1.20
    outheast
    1.18
     valued
    1.17
    culosis
    1.15
    Act Density 0.006%

    No Known Activations