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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public actions or gatherings, especially those involving voting or petitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.14
    3:0.16
    4:0.10
    5:0.06
    6:0.04
    7:0.05
    8:0.05
    9:0.10
    10:0.15
    11:0.06
    Negative Logits
    ONSORED
    -1.43
    )).
    -1.35
    Attributes
    -1.30
     ausp
    -1.28
     sill
    -1.25
     interviewer
    -1.23
     myster
    -1.21
    sole
    -1.21
    ────
    -1.18
     enterprise
    -1.15
    POSITIVE LOGITS
    joice
    1.60
     ›
    1.59
    utterstock
    1.55
    rieving
    1.53
     downed
    1.45
    unning
    1.35
    ustomed
    1.33
     rejoice
    1.31
    aste
    1.24
    icas
    1.23
    Act Density 0.429%

    No Known Activations