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

    Neuronpedia

    INDEX
    Explanations

    prepositions used to indicate locations or relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.07
    3:0.05
    4:0.21
    5:0.02
    6:0.04
    7:0.34
    8:0.03
    9:0.03
    10:0.06
    11:0.05
    Negative Logits
    buster
    -1.67
    uart
    -1.63
    malink
    -1.59
    baugh
    -1.58
    III
    -1.50
    utenberg
    -1.48
    angler
    -1.48
    prototype
    -1.47
    tsky
    -1.46
    roit
    -1.44
    POSITIVE LOGITS
     hither
    1.77
     collabor
    1.63
     unpredict
    1.58
     punishments
    1.58
     rewards
    1.57
     derog
    1.54
     bounty
    1.51
     refunds
    1.51
     bount
    1.50
    wards
    1.49
    Act Density 0.000%

    No Known Activations