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

    Neuronpedia

    INDEX
    Explanations

    structural elements or formatting cues in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inel
    -0.15
    ÑģÑĤеÑĢ
    -0.15
    ission
    -0.15
    QS
    -0.14
    ÛĮا
    -0.14
    issions
    -0.14
    allback
    -0.14
     Hammond
    -0.14
    hta
    -0.14
    lernen
    -0.14
    POSITIVE LOGITS
     cat
    0.16
     Cat
    0.16
    toolbox
    0.15
    olta
    0.15
     Nic
    0.15
    xing
    0.15
     duty
    0.15
    ago
    0.14
    olds
    0.14
    xB
    0.14
    Act Density 0.024%

    No Known Activations