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

    Neuronpedia

    INDEX
    Explanations

    contextual descriptions or evaluations of situations, typically with a focus on the impact or consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to a subject or topic that is consistently reiterated throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.55
    arthed
    -0.53
    oided
    -0.51
    Limit
    -0.50
     Vehicle
    -0.49
     welcome
    -0.49
     Panel
    -0.49
     Balloon
    -0.48
     dex
    -0.48
     Gifts
    -0.48
    POSITIVE LOGITS
    alian
    1.40
    chy
    1.34
    self
    1.21
    atic
    1.16
    unes
    1.14
    atically
    1.04
    iner
    0.88
    ovie
    0.86
    EMS
    0.83
    selves
    0.82
    Act Density 0.143%

    No Known Activations