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

    Neuronpedia

    INDEX
    Explanations

    references to edits and updates in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rone
    -0.17
    çĽ
    -0.15
    OME
    -0.15
    anton
    -0.15
    Pg
    -0.15
    .esp
    -0.14
    mont
    -0.14
    ترÛĮÙĨ
    -0.14
    date
    -0.14
     Gill
    -0.13
    POSITIVE LOGITS
    ycz
    0.15
    iros
    0.15
    odem
    0.15
    ismet
    0.15
     Helena
    0.15
     twice
    0.14
    uisse
    0.14
    zb
    0.14
    uitka
    0.14
    logy
    0.14
    Act Density 0.006%

    No Known Activations