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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.26
    2:0.07
    3:0.06
    4:0.04
    5:0.02
    6:0.09
    7:0.09
    8:0.02
    9:0.05
    10:0.09
    11:0.07
    Negative Logits
     reactive
    -2.65
     Fuk
    -2.62
    ��
    -2.47
    ulum
    -2.45
    eger
    -2.37
     reflective
    -2.25
     Rouhani
    -2.24
     Veh
    -2.20
     concrete
    -2.18
     sustained
    -2.18
    POSITIVE LOGITS
     Uncle
    6.77
     Aunt
    5.82
    uncle
    5.31
     uncle
    4.92
     aunt
    4.88
     nephew
    4.51
     Cous
    4.15
     niece
    4.04
     cousin
    3.93
    unts
    3.81
    Act Density 0.012%

    No Known Activations