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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases related to challenges and issues in various societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.17
     via
    -0.16
    ,
    -0.16
     or
    -0.15
     Brett
    -0.15
    iek
    -0.15
     Ben
    -0.15
    .
    -0.14
     '
    -0.14
     Cole
    -0.14
    POSITIVE LOGITS
    лÑĥб
    0.15
    erre
    0.15
     moden
    0.15
     nuest
    0.15
    elters
    0.14
    íĨłíĨł
    0.14
    SetBranch
    0.14
    PTR
    0.14
    OffsetTable
    0.14
    ÐIJÑĢÑħÑĸв
    0.14
    Act Density 0.172%

    No Known Activations