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

    Neuronpedia

    INDEX
    Explanations

    brain-related terms, particularly variations of the word "rad" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iw
    -0.17
    ffset
    -0.17
    ably
    -0.16
    i
    -0.16
    и
    -0.15
    ystone
    -0.15
    eel
    -0.15
    iya
    -0.15
    antro
    -0.15
    課
    -0.14
    POSITIVE LOGITS
    cliffe
    0.25
    isson
    0.22
    ishes
    0.21
    icals
    0.20
    ziej
    0.19
    olph
    0.19
    olf
    0.18
     Rad
    0.18
    elaide
    0.18
    ical
    0.18
    Act Density 0.010%

    No Known Activations