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

    Neuronpedia

    INDEX
    Explanations

    political party affiliations and their percentages in survey responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.13
    3:0.24
    4:0.12
    5:0.05
    6:0.03
    7:0.03
    8:0.06
    9:0.05
    10:0.10
    11:0.10
    Negative Logits
    osponsors
    -1.53
    kefeller
    -1.52
    )!
    -1.46
    WARE
    -1.43
    ortment
    -1.38
    AAAAAAAA
    -1.37
     FANT
    -1.36
    HOME
    -1.35
    ivered
    -1.35
    機
    -1.33
    POSITIVE LOGITS
    orem
    1.47
     Val
    1.43
     Sullivan
    1.41
    chu
    1.37
     Engel
    1.35
     Torres
    1.33
     Maz
    1.33
     Philippe
    1.29
     Stella
    1.28
    acion
    1.28
    Act Density 0.006%

    No Known Activations