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

    Neuronpedia

    INDEX
    Explanations

    statements and arguments related to legal and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igner
    -0.16
    _blend
    -0.15
    ilyn
    -0.15
    vell
    -0.15
    lev
    -0.15
     Dys
    -0.15
    .ndim
    -0.15
     Sparks
    -0.14
    quet
    -0.14
    ì²Ń
    -0.14
    POSITIVE LOGITS
     quot
    0.15
    arak
    0.14
     too
    0.14
    -too
    0.14
     Victim
    0.14
     implicit
    0.14
    too
    0.14
    ारà¤ķ
    0.14
     Lod
    0.14
    inz
    0.13
    Act Density 0.173%

    No Known Activations