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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and relationships between variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.43
     re
    -0.42
    ecto
    -0.41
     Him
    -0.40
     above
    -0.39
    Description
    -0.39
    äsident
    -0.38
     معه
    -0.38
    RTHOOK
    -0.38
    completo
    -0.37
    POSITIVE LOGITS
    IntoConstraints
    0.88
    UnusedPrivate
    0.77
     referrerpolicy
    0.71
    
    0.69
    estacks
    0.67
     JpaRepository
    0.63
    findpost
    0.63
    PointerException
    0.63
    ptonshire
    0.62
    horabuena
    0.61
    Act Density 0.551%

    No Known Activations