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

    Neuronpedia

    INDEX
    Explanations

    references to online platforms or content creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.13
    1:0.02
    2:0.30
    3:0.03
    4:0.04
    5:0.04
    6:0.04
    7:0.08
    8:0.09
    9:0.02
    10:0.04
    11:0.10
    Negative Logits
    ...]
    -2.31
    selection
    -2.24
     bonuses
    -2.18
     NPCs
    -2.16
     rewards
    -2.15
     retaining
    -2.07
    :]
    -2.05
    uses
    -1.99
    children
    -1.97
    orsi
    -1.92
    POSITIVE LOGITS
     Joined
    3.95
    Joined
    2.93
    76561
    2.65
     Born
    2.60
    �
    2.51
     Unloaded
    2.48
    セ
    2.43
    Born
    2.28
    ヘ
    2.27
    ジ
    2.26
    Act Density 0.000%

    No Known Activations