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

    Neuronpedia

    INDEX
    Explanations

    content related to systemic issues and historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.06
    3:0.05
    4:0.09
    5:0.03
    6:0.04
    7:0.39
    8:0.03
    9:0.03
    10:0.07
    11:0.09
    Negative Logits
    mouth
    -1.75
    eye
    -1.74
    ople
    -1.44
    ichick
    -1.41
    rict
    -1.38
    iden
    -1.37
    �
    -1.37
    fax
    -1.35
    bear
    -1.34
     eyed
    -1.34
    POSITIVE LOGITS
     victories
    1.60
    ��
    1.60
     Renew
    1.54
     Memories
    1.54
     veter
    1.53
     legacy
    1.52
     millenn
    1.52
    lore
    1.48
     achievements
    1.48
     Generations
    1.47
    Act Density 0.004%

    No Known Activations