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

    Neuronpedia

    INDEX
    Explanations

    names and surnames of people

    oai_token-act-pair · gpt-3.5-turbo

    names and references to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osuke
    -0.76
     Azerb
    -0.69
    ourced
    -0.65
    IDS
    -0.60
    uthor
    -0.60
    ettle
    -0.59
    ADRA
    -0.59
    é¾
    -0.58
    obos
    -0.57
     cogn
    -0.57
    POSITIVE LOGITS
    ts
    1.58
    t
    1.51
    tes
    1.39
    te
    1.32
    ta
    1.27
    ty
    1.26
    ted
    1.23
    tin
    1.20
    tt
    1.20
    ting
    1.18
    Act Density 0.231%

    No Known Activations