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

    Neuronpedia

    INDEX
    Explanations

    terms related to relationships and editions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hirts
    -0.83
    /***/
    -0.80
    delaire
    -0.79
    astrar
    -0.77
    orszá
    -0.77
     estekak
    -0.77
    entant
    -0.73
     Duarte
    -0.72
     Deum
    -0.71
     immunos
    -0.70
    POSITIVE LOGITS
    Edition
    1.14
    edition
    1.12
    ITION
    1.11
     Edition
    1.09
     edition
    0.96
    ection
    0.93
    ation
    0.93
     EDITION
    0.90
    NATION
    0.87
    ally
    0.85
    Act Density 0.180%

    No Known Activations