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

    Neuronpedia

    INDEX
    Explanations

    elements related to dates and references to articles or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oki
    -0.15
    iden
    -0.14
    Redux
    -0.14
    ula
    -0.14
    usan
    -0.14
    iser
    -0.14
    udget
    -0.13
     è¡
    -0.13
    iler
    -0.13
    î
    -0.13
    POSITIVE LOGITS
    _ASSUME
    0.14
    .between
    0.14
    adolu
    0.13
    errupted
    0.13
    -unstyled
    0.13
     ãĥ¯
    0.13
    ething
    0.12
    Ā
    0.12
    ñana
    0.12
    .truth
    0.12
    Act Density 0.200%

    No Known Activations