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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political commentary and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.04
    3:0.04
    4:0.03
    5:0.03
    6:0.03
    7:0.43
    8:0.02
    9:0.04
    10:0.13
    11:0.12
    Negative Logits
    vable
    -1.51
     competition
    -1.51
     relegation
    -1.50
     aisle
    -1.46
     bargaining
    -1.42
     basket
    -1.42
     negoti
    -1.41
     paramedics
    -1.37
     bidder
    -1.36
     orchestra
    -1.35
    POSITIVE LOGITS
    Tweet
    1.77
    warning
    1.70
     tweets
    1.66
    javascript
    1.59
    weet
    1.59
    ティ
    1.58
    message
    1.55
    delete
    1.53
    Hello
    1.53
    Twitter
    1.51
    Act Density 0.042%

    No Known Activations