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

    Neuronpedia

    INDEX
    Explanations

    phrases involving revelation or uncovering details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.06
    3:0.09
    4:0.29
    5:0.04
    6:0.03
    7:0.12
    8:0.05
    9:0.03
    10:0.10
    11:0.07
    Negative Logits
    ourt
    -1.67
     rave
    -1.60
     bothered
    -1.53
     roundup
    -1.49
     uproar
    -1.43
     aired
    -1.42
     antiv
    -1.42
     approves
    -1.41
    Davis
    -1.39
     preseason
    -1.38
    POSITIVE LOGITS
     hidden
    1.93
    hidden
    1.76
    itives
    1.74
     treasures
    1.70
    stery
    1.69
    selves
    1.66
     harmless
    1.61
     treasure
    1.60
    ifacts
    1.51
     fug
    1.48
    Act Density 0.003%

    No Known Activations