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

    Neuronpedia

    INDEX
    Explanations

    noun phrases indicating possession or affiliation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.12
    3:0.06
    4:0.20
    5:0.02
    6:0.03
    7:0.32
    8:0.02
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
    alach
    -1.81
    phe
    -1.72
    sburgh
    -1.63
    oother
    -1.58
    swick
    -1.57
    culosis
    -1.57
    Merit
    -1.53
    anamo
    -1.47
    oried
    -1.47
    buster
    -1.46
    POSITIVE LOGITS
     whim
    1.56
     legislatures
    1.55
     discretion
    1.51
     mortals
    1.49
     dictated
    1.48
     scheduling
    1.47
     circumstance
    1.47
     strangers
    1.47
     whims
    1.47
     rulings
    1.45
    Act Density 0.000%

    No Known Activations