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

    Neuronpedia

    INDEX
    Explanations

    political or governmental terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    important numerical references or comparisons in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apons
    -0.72
    使
    -0.64
    dinand
    -0.63
    anooga
    -0.63
    >]
    -0.63
    orum
    -0.59
    æѦ
    -0.58
    zhou
    -0.58
    anche
    -0.55
    anners
    -0.55
    POSITIVE LOGITS
     nutshell
    0.71
     coincidence
    0.69
     itch
    0.65
     pecul
    0.59
     kinda
    0.57
     hypocrisy
    0.55
     funny
    0.52
     squirrel
    0.52
     crochet
    0.52
     coward
    0.52
    Act Density 0.869%

    No Known Activations