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

    Neuronpedia

    INDEX
    Explanations

    references to significant actions or statements made by political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.05
    2:0.09
    3:0.11
    4:0.07
    5:0.08
    6:0.08
    7:0.08
    8:0.07
    9:0.07
    10:0.08
    11:0.07
    Negative Logits
     Samoa
    -1.83
     McA
    -1.59
     Knox
    -1.59
     Advertising
    -1.54
    �
    -1.51
     Surv
    -1.50
    ゴン
    -1.50
     Shutterstock
    -1.48
     Died
    -1.47
    エル
    -1.42
    POSITIVE LOGITS
     bends
    1.60
     disg
    1.60
     waits
    1.57
    hatt
    1.56
     trickle
    1.54
    ]]
    1.53
    ggle
    1.52
    anke
    1.51
    dozen
    1.46
    gencies
    1.45
    Act Density 0.000%

    No Known Activations