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

    Neuronpedia

    INDEX
    Explanations

    words related to the city of Toronto, with a particular focus on "ont" at the end of words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "kont" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loo
    -0.84
    GBT
    -0.76
    glers
    -0.70
    BILITIES
    -0.70
    ulative
    -0.69
     JPM
    -0.68
    tips
    -0.68
    OTS
    -0.67
    gb
    -0.64
    iliar
    -0.64
    POSITIVE LOGITS
    rol
    1.08
    ology
    1.02
    gomery
    1.01
    ological
    0.97
    ract
    0.94
    ologist
    0.94
    ario
    0.93
    ractor
    0.92
    ainment
    0.91
    osaurus
    0.90
    Act Density 0.029%

    No Known Activations