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

    Neuronpedia

    INDEX
    Explanations

    key political figures or prominent names in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.11
    3:0.10
    4:0.17
    5:0.05
    6:0.08
    7:0.14
    8:0.05
    9:0.06
    10:0.08
    11:0.07
    Negative Logits
    Material
    -1.88
    inventoryQuantity
    -1.83
    ーク
    -1.66
    Alias
    -1.62
    Quant
    -1.62
    Untitled
    -1.58
    Rat
    -1.58
    /**
    -1.53
    Basic
    -1.51
    Books
    -1.49
    POSITIVE LOGITS
    versely
    1.68
    nces
    1.64
    rique
    1.61
    rompt
    1.58
     valleys
    1.53
     luckily
    1.52
    rha
    1.51
    jer
    1.48
    leep
    1.48
     staggered
    1.47
    Act Density 0.000%

    No Known Activations