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

    Neuronpedia

    INDEX
    Explanations

    the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.10
    2:0.09
    3:0.07
    4:0.06
    5:0.08
    6:0.07
    7:0.06
    8:0.08
    9:0.09
    10:0.06
    11:0.07
    Negative Logits
    WHERE
    -1.91
    abled
    -1.71
    medium
    -1.67
    hett
    -1.65
    lying
    -1.62
     lined
    -1.61
    hops
    -1.60
     verbally
    -1.59
     populated
    -1.58
     repeat
    -1.57
    POSITIVE LOGITS
     Piercing
    1.98
     Wraith
    1.81
    cean
    1.76
     Bacon
    1.71
     Reneg
    1.70
     Crusade
    1.68
     Juno
    1.65
     Ae
    1.63
     Tomato
    1.62
     Reincarn
    1.62
    Act Density 0.000%

    No Known Activations