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

    Neuronpedia

    INDEX
    Explanations

    occurrences and contexts of the word "loss" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utsch
    -0.17
    eer
    -0.15
    ize
    -0.15
    kins
    -0.15
    /lists
    -0.14
    prise
    -0.14
    ì°©
    -0.14
    -align
    -0.14
    lia
    -0.14
     Collapse
    -0.14
    POSITIVE LOGITS
    (es
    0.25
    ess
    0.22
     mát
    0.22
     Angeles
    0.21
    y
    0.20
    /change
    0.20
    ses
    0.20
    es
    0.19
     Prevention
    0.19
    lessly
    0.18
    Act Density 0.033%

    No Known Activations