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

    Neuronpedia

    INDEX
    Explanations

    references to classic literary works and their summaries or analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itol
    -0.16
    ond
    -0.16
    iam
    -0.15
     PR
    -0.15
    itos
    -0.15
     advance
    -0.15
    a
    -0.15
     -
    -0.15
     phase
    -0.14
     cavern
    -0.14
    POSITIVE LOGITS
    geh
    0.17
    vang
    0.16
    arro
    0.16
    /compiler
    0.15
    δÏĮ
    0.15
    ouden
    0.15
     Yön
    0.15
     sefer
    0.14
    lio
    0.14
    Ùĥت
    0.14
    Act Density 0.480%

    No Known Activations