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

    Neuronpedia

    INDEX
    Explanations

    mentions of the president and their actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.04
    3:0.05
    4:0.04
    5:0.06
    6:0.03
    7:0.03
    8:0.05
    9:0.06
    10:0.41
    11:0.14
    Negative Logits
     Tek
    -1.64
     Crescent
    -1.60
     sect
    -1.42
    ournals
    -1.42
     Dek
    -1.40
     plantations
    -1.39
     Gree
    -1.37
    tex
    -1.35
     chic
    -1.34
     Moor
    -1.33
    POSITIVE LOGITS
    ��
    1.65
    iciary
    1.65
    ��
    1.62
    otonin
    1.57
     Surface
    1.52
    izzard
    1.51
    hower
    1.45
     pardon
    1.44
    soever
    1.43
    ��
    1.42
    Act Density 0.073%

    No Known Activations