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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public and media discourse on controversial topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.05
    4:0.06
    5:0.02
    6:0.48
    7:0.04
    8:0.04
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
    ortium
    -1.76
    lished
    -1.73
    ificantly
    -1.61
    anwhile
    -1.59
     GOODMAN
    -1.57
    assium
    -1.56
    etheus
    -1.56
    EStream
    -1.51
    isSpecialOrderable
    -1.45
    theless
    -1.44
    POSITIVE LOGITS
    sounding
    1.45
    folk
    1.36
    glers
    1.36
    smanship
    1.35
    national
    1.28
    bur
    1.28
    ocratic
    1.28
    aggressive
    1.24
    isms
    1.24
    ilian
    1.24
    Act Density 0.861%

    No Known Activations