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

    Neuronpedia

    INDEX
    Explanations

    references to internal systems and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.83
     McClure
    -0.82
    ]")]
    -0.77
    Geplaatst
    -0.75
     équipée
    -0.71
    ToLeft
    -0.69
     brady
    -0.68
    displayquote
    -0.68
     Obamacare
    -0.67
    ☝
    -0.67
    POSITIVE LOGITS
     Internal
    1.75
     internal
    1.70
     INTERNAL
    1.62
    Internal
    1.56
     internally
    1.43
    internal
    1.41
    INTERNAL
    1.31
     Intern
    1.26
    ternal
    1.26
    InternalFrame
    1.16
    Act Density 0.102%

    No Known Activations