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

    Neuronpedia

    INDEX
    Explanations

    references to friendship or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.06
    5:0.08
    6:0.09
    7:0.07
    8:0.08
    9:0.07
    10:0.10
    11:0.08
    Negative Logits
    %%
    -2.81
    (),
    -2.78
    ().
    -2.62
    .#
    -2.53
    .<
    -2.50
    warts
    -2.41
    acid
    -2.37
    +)
    -2.33
     poisoning
    -2.29
    ogun
    -2.29
    POSITIVE LOGITS
    ◼
    3.07
     Mari
    2.85
     Lam
    2.73
     Syri
    2.56
     Stam
    2.53
    ivably
    2.40
     Beir
    2.38
    namese
    2.33
     Sau
    2.32
     UCHIJ
    2.32
    Act Density 0.000%

    No Known Activations