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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.04
    3:0.07
    4:0.04
    5:0.04
    6:0.32
    7:0.21
    8:0.04
    9:0.04
    10:0.04
    11:0.05
    Negative Logits
     volunt
    -1.47
    Pool
    -1.42
    duc
    -1.40
    cube
    -1.40
     reinforcement
    -1.38
    ão
    -1.28
     enh
    -1.27
     wik
    -1.24
    tree
    -1.24
    pool
    -1.23
    POSITIVE LOGITS
    METHOD
    1.47
    田
    1.44
    CTV
    1.42
    ATIONAL
    1.35
    ACP
    1.32
    colm
    1.29
    Enlarge
    1.28
    philis
    1.26
    シ
    1.26
    culosis
    1.26
    Act Density 0.000%

    No Known Activations