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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itself
    -0.20
    onde
    -0.18
    estroy
    -0.16
     Saud
    -0.16
    kest
    -0.15
    eren
    -0.15
    sted
    -0.15
    Uvs
    -0.15
    iders
    -0.15
    виÑĤ
    -0.15
    POSITIVE LOGITS
     whom
    0.28
     whose
    0.24
    whose
    0.20
    -eslint
    0.16
     figure
    0.16
    身ä¸Ĭ
    0.15
    åIJįåīį
    0.15
    haust
    0.15
     name
    0.15
    osh
    0.14
    Act Density 0.315%

    No Known Activations