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

    Neuronpedia

    INDEX
    Explanations

    the presence of unique identifiers or proper nouns, particularly in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    e
    -0.32
    i
    -0.28
    eil
    -0.23
    eer
    -0.23
    ozy
    -0.22
    ech
    -0.21
    eless
    -0.20
    ees
    -0.20
    eel
    -0.20
    eck
    -0.19
    POSITIVE LOGITS
    ud
    0.25
    apest
    0.24
    ges
    0.24
    dest
    0.23
    ying
    0.22
    icial
    0.22
    lej
    0.22
    gment
    0.21
    ley
    0.21
    udy
    0.21
    Act Density 0.019%

    No Known Activations