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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a method or strategy for achieving a specific goal

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating a method or approach to achieving various outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usters
    -0.80
    uster
    -0.75
    iries
    -0.69
     Aure
    -0.64
    akov
    -0.62
    iasco
    -0.61
    arthed
    -0.61
    unes
    -0.61
     livest
    -0.61
    inating
    -0.60
    POSITIVE LOGITS
    fare
    1.15
    finding
    1.04
    point
    1.01
    ward
    1.00
    finder
    0.86
    forward
    0.85
    WARD
    0.82
    points
    0.78
    kell
    0.72
     forward
    0.71
    Act Density 0.032%

    No Known Activations