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

    Neuronpedia

    INDEX
    Explanations

    complex lexical structures related to social dynamics and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.01
    2:0.11
    3:0.15
    4:0.29
    5:0.03
    6:0.04
    7:0.04
    8:0.08
    9:0.06
    10:0.05
    11:0.05
    Negative Logits
     reminded
    -1.79
    terday
    -1.61
    田
    -1.58
    enos
    -1.57
    76561
    -1.57
    urai
    -1.56
    soon
    -1.56
    ��
    -1.50
    �醒
    -1.47
    uyomi
    -1.46
    POSITIVE LOGITS
     altogether
    1.66
     ones
    1.62
     equivalents
    1.51
     nor
    1.41
     originals
    1.40
     darts
    1.34
     actual
    1.30
     pills
    1.27
     rud
    1.26
     conventional
    1.26
    Act Density 0.044%

    No Known Activations