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

    Neuronpedia

    INDEX
    Explanations

    contexts related to political positions and governmental roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.41
    3:0.03
    4:0.03
    5:0.02
    6:0.05
    7:0.05
    8:0.03
    9:0.03
    10:0.16
    11:0.05
    Negative Logits
     GOODMAN
    -2.77
    iosyn
    -2.58
     simul
    -2.43
     plaza
    -2.40
     <@
    -2.27
     awa
    -2.22
     poppy
    -2.16
    ベ
    -2.14
     autom
    -2.13
    milo
    -2.10
    POSITIVE LOGITS
    d
    3.79
    D
    3.72
    ds
    3.52
    Ds
    3.39
    DD
    3.33
    DF
    3.32
    DERR
    3.21
    dd
    3.11
    dal
    3.10
    DL
    3.04
    Act Density 0.018%

    No Known Activations