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

    Neuronpedia

    INDEX
    Explanations

    instances of direct quotations or dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .datab
    -0.16
    anca
    -0.15
     Zust
    -0.15
    лÑıн
    -0.15
     Webster
    -0.14
    ETY
    -0.14
     wonder
    -0.14
    ground
    -0.13
    Ĭ¶
    -0.13
    emma
    -0.13
    POSITIVE LOGITS
    -Mart
    0.14
    esini
    0.14
    Probe
    0.14
    ëł¥ìĿ´
    0.14
    ẩy
    0.13
    illions
    0.13
    anner
    0.13
     plag
    0.13
    /Dk
    0.13
    untu
    0.13
    Act Density 0.068%

    No Known Activations