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

    Neuronpedia

    INDEX
    Explanations

    possessive constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.09
    4:0.07
    5:0.09
    6:0.06
    7:0.07
    8:0.08
    9:0.10
    10:0.08
    11:0.07
    Negative Logits
    hap
    -1.77
     yawn
    -1.72
     Cheong
    -1.71
     record
    -1.70
     tallest
    -1.58
     Jinn
    -1.55
     column
    -1.54
     marble
    -1.45
     valves
    -1.43
    ��
    -1.43
    POSITIVE LOGITS
     advoc
    1.87
    ivals
    1.85
    akedown
    1.73
     therap
    1.71
     Deaths
    1.69
    authorized
    1.58
    ��
    1.56
    please
    1.55
    asters
    1.55
    gee
    1.51
    Act Density 0.000%

    No Known Activations