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

    Neuronpedia

    INDEX
    Explanations

    references to qualities and attributes of objects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HomeAsUpEnabled
    -0.73
    verwijspagina
    -0.72
     jdbcTemplate
    -0.70
    脚注の使い方
    -0.68
     whoſe
    -0.67
    SequentialGroup
    -0.66
    ImageIO
    -0.65
     myſelf
    -0.65
     pleaſure
    -0.64
    enumii
    -0.63
    POSITIVE LOGITS
     characteristics
    1.73
    characteristics
    1.48
     Characteristics
    1.46
     characteristic
    1.44
     traits
    1.41
    Characteristics
    1.37
     qualities
    1.30
     Eigenschaften
    1.26
     caractéristique
    1.23
     properties
    1.23
    Act Density 0.350%

    No Known Activations