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

    Neuronpedia

    INDEX
    Explanations

    instances of confrontation and forms related to processing or procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umen
    -0.18
    elling
    -0.17
    iates
    -0.16
    iate
    -0.16
    ÙĬار
    -0.15
     Barth
    -0.15
    ially
    -0.14
    olding
    -0.14
    swith
    -0.14
    oring
    -0.14
    POSITIVE LOGITS
    ations
    0.76
    ATIONS
    0.50
    ational
    0.50
    ation
    0.42
    ative
    0.40
    acion
    0.40
    ación
    0.40
    ATION
    0.39
    aciones
    0.37
    ationToken
    0.37
    Act Density 0.091%

    No Known Activations