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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mathematical proofs and generalizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </thead>
    -0.77
     cherchés
    -0.71
    principalTable
    -0.68
     للمعارف
    -0.67
    twimg
    -0.66
     "..\..\..\
    -0.65
     estimés
    -0.65
    OGND
    -0.63
    JdbcTemplate
    -0.62
    archiviato
    -0.62
    POSITIVE LOGITS
     general
    1.68
    general
    1.49
    General
    1.33
     General
    1.27
     GENERAL
    1.25
     generale
    1.22
     général
    1.19
     generales
    1.15
    GENERAL
    1.15
     geral
    1.13
    Act Density 0.875%

    No Known Activations