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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating temporal events and specific occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.10
    3:0.06
    4:0.14
    5:0.02
    6:0.04
    7:0.36
    8:0.03
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
     administ
    -1.71
    ealous
    -1.64
    lled
    -1.56
     lawy
    -1.56
    staking
    -1.54
     persuaded
    -1.52
     oath
    -1.48
     abst
    -1.48
    administ
    -1.48
     topic
    -1.46
    POSITIVE LOGITS
     Thumbnails
    1.75
    Vision
    1.60
    opia
    1.58
    Ther
    1.57
     Refugees
    1.55
     Exhibit
    1.52
     Crate
    1.52
    Glass
    1.44
     Pulse
    1.42
    Rot
    1.41
    Act Density 0.016%

    No Known Activations