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

    Neuronpedia

    INDEX
    Explanations

    mentions of loss and its implications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utsch
    -0.20
    eer
    -0.16
    lia
    -0.16
    /lists
    -0.16
    cerr
    -0.14
    èµ·æĿ¥
    -0.14
    izio
    -0.14
    kins
    -0.14
     gauche
    -0.14
    tron
    -0.14
    POSITIVE LOGITS
    -loss
    0.23
     Angeles
    0.21
    y
    0.20
    /change
    0.20
    (es
    0.19
    ess
    0.19
     mát
    0.19
    ses
    0.17
     sight
    0.17
    ssp
    0.16
    Act Density 0.028%

    No Known Activations