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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the suffix "ian" in proper names or nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IVE
    -0.79
    urers
    -0.72
    uring
    -0.71
    door
    -0.70
    ively
    -0.67
    IRT
    -0.66
    urer
    -0.66
    URES
    -0.65
    ridges
    -0.64
     adolesc
    -0.64
    POSITIVE LOGITS
    nis
    1.38
    thus
    1.27
    na
    1.23
    apolis
    1.08
    ni
    1.06
    nen
    1.03
    ne
    1.02
    throp
    1.01
    opolis
    0.97
    akis
    0.95
    Act Density 0.090%

    No Known Activations