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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and words indicating measurement or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.36
    2:0.03
    3:0.03
    4:0.03
    5:0.22
    6:0.04
    7:0.02
    8:0.04
    9:0.04
    10:0.03
    11:0.03
    Negative Logits
    覚醒
    -1.82
    ria
    -1.75
    EStream
    -1.68
    ↵ 
    -1.66
     MODULE
    -1.65
    gi
    -1.63
     Symphony
    -1.61
     Institutes
    -1.59
     Meteor
    -1.57
    idas
    -1.57
    POSITIVE LOGITS
    up
    2.50
     up
    2.00
    forth
    1.95
    apse
    1.93
     Up
    1.92
    �
    1.89
    UP
    1.87
    ups
    1.83
    Up
    1.81
     ups
    1.76
    Act Density 0.006%

    No Known Activations