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

    Neuronpedia

    INDEX
    Explanations

    terms related to compression and compacting processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Péri
    -0.55
    Continuation
    -0.54
    飘
    -0.54
    ogna
    -0.54
     GetEnumerator
    -0.52
    ⎩
    -0.51
     Aussch
    -0.50
    ते
    -0.50
    yssey
    -0.50
    Portail
    -0.49
    POSITIVE LOGITS
     compressed
    1.07
    PRESS
    0.99
     pressing
    0.98
     presses
    0.97
     pressed
    0.97
     crushing
    0.95
     crush
    0.95
     squeezing
    0.95
     Compressed
    0.95
     squeeze
    0.94
    Act Density 0.408%

    No Known Activations