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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to energy loss and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    losses per cow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.54
     ligiloj
    -0.49
    EndGlobalSection
    -0.48
    цездатний
    -0.47
    homonymie
    -0.45
    ']):
    -0.43
    liſh
    -0.43
    tagHelper
    -0.42
    EndContext
    -0.41
    UserScript
    -0.41
    POSITIVE LOGITS
     loss
    1.51
     losses
    1.34
     Loss
    1.31
    Loss
    1.28
     lost
    1.28
    loss
    1.24
     lose
    1.23
     LOSS
    1.23
     losing
    1.19
    Lost
    1.19
    Act Density 0.092%

    No Known Activations