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

    Neuronpedia

    INDEX
    Explanations

    phrases related to awareness and communication about situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.05
    3:0.18
    4:0.06
    5:0.36
    6:0.02
    7:0.10
    8:0.03
    9:0.02
    10:0.05
    11:0.04
    Negative Logits
     my
    -4.18
     me
    -3.95
     myself
    -3.82
     I
    -3.19
    my
    -2.98
     My
    -2.88
     mine
    -2.88
    My
    -2.83
     MY
    -2.77
    I
    -2.53
    POSITIVE LOGITS
    ukes
    2.13
    acks
    1.99
     Royale
    1.99
     abusers
    1.94
    zb
    1.92
    letes
    1.89
    kos
    1.88
    phan
    1.85
    umar
    1.85
     Braz
    1.83
    Act Density 0.735%

    No Known Activations