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

    Neuronpedia

    INDEX
    Explanations

    words and terms related to programming and computational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    u
    -0.28
    at
    -0.28
    y
    -0.26
    ar
    -0.23
    g
    -0.23
    i
    -0.23
    athy
    -0.21
    iw
    -0.21
    yat
    -0.21
    aron
    -0.20
    POSITIVE LOGITS
    es
    0.17
    resent
    0.17
    ares
    0.17
    hton
    0.16
    lication
    0.16
    lications
    0.16
    ertoire
    0.16
    nier
    0.16
    licative
    0.15
    ener
    0.15
    Act Density 0.087%

    No Known Activations