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

    Neuronpedia

    INDEX
    Explanations

    concepts related to quantum mechanics and physical states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     −
    -1.15
    −
    -1.14
       
    -1.12
     ______
    -1.06
    ffi
    -1.05
     \[
    -1.03
                                   
    -1.02
     ________
    -0.99
     __________
    -0.93
                 
    -0.92
    POSITIVE LOGITS
    ..
    2.84
    )..
    2.42
    "..
    2.09
    '..
    2.07
     ..
    2.02
    ..”
    1.98
    .."
    1.96
    ..)
    1.91
    ..(
    1.85
    ,..
    1.76
    Act Density 0.169%

    No Known Activations