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

    Neuronpedia

    INDEX
    Explanations

    terms related to loss or defeat

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     loose
    -0.92
    loose
    -0.80
    Loose
    -0.80
     Loose
    -0.72
     esque
    -0.70
    LEncoder
    -0.68
    ureka
    -0.67
    SKE
    -0.64
    ✨:
    -0.62
     esquecer
    -0.61
    POSITIVE LOGITS
     loss
    2.64
     Loss
    2.42
    Loss
    2.28
    loss
    2.21
     LOSS
    2.16
    LOSS
    1.91
     losses
    1.79
     Losses
    1.59
     Verlust
    1.56
     perte
    1.53
    Act Density 0.163%

    No Known Activations