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

    Neuronpedia

    INDEX
    Explanations

    the term indicating close interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.09
    7:0.07
    8:0.07
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    ublic
    -2.96
     Democr
    -2.91
     behavi
    -2.82
    BLIC
    -2.61
     democracies
    -2.55
    MOD
    -2.51
    ategic
    -2.50
    Dynamic
    -2.49
    ospons
    -2.48
     Democracy
    -2.48
    POSITIVE LOGITS
    ":["
    3.29
     Osw
    2.68
     Bolt
    2.54
     Rose
    2.49
     Gat
    2.49
     Romanian
    2.46
     Gem
    2.40
     Decker
    2.39
     CU
    2.38
     Crate
    2.36
    Act Density 0.000%

    No Known Activations