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

    Neuronpedia

    INDEX
    Explanations

    references to loss and its quantification in various contexts

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

    loss of something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.42
    AnchorStyles
    -0.40
    
    -0.37
    writeFieldEnd
    -0.36
    WebServlet
    -0.33
    exempt
    -0.33
     uitge
    -0.33
     Skip
    -0.33
    ɕ
    -0.33
    antaranya
    -0.32
    POSITIVE LOGITS
     loss
    0.74
     lost
    0.68
    loss
    0.67
     lose
    0.63
    Lost
    0.59
    lost
    0.59
    Loss
    0.59
     LOST
    0.59
     Lost
    0.58
     Loss
    0.57
    Act Density 0.018%

    No Known Activations