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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intent and purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.52
    ix
    -0.48
    7
    -0.47
    odo
    -0.47
     are
    -0.45
    4
    -0.44
    5
    -0.43
    </code>
    -0.43
     dont
    -0.43
    8
    -0.42
    POSITIVE LOGITS
    Portale
    1.17
    HasAnnotation
    0.99
     للمعارف
    0.99
     Majefty
    0.99
     surla
    0.95
     pleaſure
    0.90
    LookAnd
    0.89
    extAlignment
    0.87
    InjectAttribute
    0.87
     مشين
    0.86
    Act Density 0.543%

    No Known Activations