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

    Neuronpedia

    INDEX
    Explanations

    words related to education and academia

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and governmental concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ge
    -0.82
    grade
    -0.80
    corn
    -0.80
    ciplinary
    -0.79
    tons
    -0.79
    gate
    -0.77
    lde
    -0.76
    hex
    -0.76
    lets
    -0.76
    tery
    -0.75
    POSITIVE LOGITS
    ING
    1.85
    ERY
    1.71
    ERS
    1.71
    ED
    1.70
    ION
    1.70
    ANT
    1.70
    ER
    1.66
    ATION
    1.66
    EST
    1.65
    IBLE
    1.65
    Act Density 0.175%

    No Known Activations