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

    Neuronpedia

    INDEX
    Explanations

    names starting with "Ruf" or a variation in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific name or term related to an individual or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Siren
    -0.69
     Clash
    -0.64
    dry
    -0.63
     Cyborg
    -0.63
     ashore
    -0.61
    nesia
    -0.61
     Sapphire
    -0.59
     Dragonbound
    -0.59
    aths
    -0.57
     deaf
    -0.56
    POSITIVE LOGITS
    imates
    0.92
    req
    0.88
    orce
    0.84
    sch
    0.81
    uese
    0.79
    doms
    0.78
    eatures
    0.77
    igi
    0.76
    inite
    0.74
    action
    0.73
    Act Density 0.037%

    No Known Activations