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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a decline or downfall

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.08
    9:0.07
    10:0.08
    11:0.08
    Negative Logits
    zai
    -2.77
    orkshire
    -2.76
    onian
    -2.75
    owder
    -2.64
     eng
    -2.62
    eton
    -2.59
     lyn
    -2.57
    collar
    -2.56
    grain
    -2.52
     heating
    -2.51
    POSITIVE LOGITS
     Cait
    2.99
     Donkey
    2.96
     Kirby
    2.91
     Yoshi
    2.85
     Rogue
    2.79
     Lucas
    2.75
     Destination
    2.75
     Pose
    2.70
     Fountain
    2.67
     Skip
    2.66
    Act Density 0.000%

    No Known Activations