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

    Neuronpedia

    INDEX
    Explanations

    numerical data or values associated with measured quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     a
    -0.87
     HH
    -0.86
     RH
    -0.86
     ET
    -0.85
    ◚
    -0.84
    娡
    -0.84
    몭
    -0.84
     PP
    -0.84
    нгред
    -0.84
     in
    -0.84
    POSITIVE LOGITS
    1
    1.30
    9
    1.16
    5
    1.12
    8
    1.11
    3
    1.11
    4
    1.09
    7
    1.08
    2
    1.07
    6
    1.04
    0
    0.84
    Act Density 1.231%

    No Known Activations