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

    Neuronpedia

    INDEX
    Explanations

    syntax-related elements in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Haram
    -0.15
     Rent
    -0.15
    bach
    -0.14
    вед
    -0.14
    anke
    -0.13
    onomy
    -0.13
    idth
    -0.13
    teÅŁ
    -0.13
    opr
    -0.13
    807
    -0.13
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.15
    ↵↵↵↵↵↵↵↵↵↵
    0.15
    ↵↵↵↵↵↵↵
    0.15
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.15
    ↵↵↵↵↵↵↵↵
    0.15
    ади
    0.15
    ause
    0.15
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.15
     public
    0.14
    ↵↵↵↵↵
    0.14
    Act Density 0.028%

    No Known Activations