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

    Neuronpedia

    INDEX
    Explanations

    topics related to social issues and public concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.41
    1:0.03
    2:0.03
    3:0.08
    4:0.06
    5:0.10
    6:0.09
    7:0.03
    8:0.04
    9:0.06
    10:0.01
    11:0.02
    Negative Logits
     biologists
    -1.75
     accompl
    -1.72
     propag
    -1.71
     sniff
    -1.71
     programmers
    -1.68
     hardened
    -1.58
     sear
    -1.57
     throats
    -1.55
     quicker
    -1.55
     managers
    -1.53
    POSITIVE LOGITS
    olitics
    1.96
    avery
    1.79
    politics
    1.78
    Politics
    1.74
    owan
    1.73
    cair
    1.73
    iculture
    1.71
    ania
    1.61
    usterity
    1.60
    independence
    1.59
    Act Density 0.007%

    No Known Activations