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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate omitted information or facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.08
    3:0.05
    4:0.14
    5:0.02
    6:0.05
    7:0.41
    8:0.04
    9:0.03
    10:0.06
    11:0.06
    Negative Logits
    anic
    -1.66
    orses
    -1.65
    rha
    -1.60
    lav
    -1.60
    wagen
    -1.55
    ivot
    -1.53
    yrinth
    -1.53
    oros
    -1.51
    rg
    -1.51
    oled
    -1.50
    POSITIVE LOGITS
     altogether
    2.01
     anymore
    1.80
     distinctions
    1.64
     jokes
    1.62
     incidentally
    1.54
     redund
    1.47
     because
    1.44
     comparisons
    1.44
     Doodle
    1.42
     comparison
    1.41
    Act Density 0.004%

    No Known Activations