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

    Neuronpedia

    INDEX
    Explanations

    phrases or acronyms related to legal or political entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "IL" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rano
    -0.85
    unin
    -0.85
    rette
    -0.83
    perature
    -0.79
    liga
    -0.74
    hra
    -0.73
    ria
    -0.73
    unia
    -0.73
     Crunch
    -0.73
    oln
    -0.73
    POSITIVE LOGITS
    ibrary
    1.19
    UTION
    1.10
    DER
    1.01
    ER
    0.97
    IAN
    0.96
    MET
    0.94
    ATER
    0.94
    HEAD
    0.93
    IENT
    0.93
    ORED
    0.92
    Act Density 0.011%

    No Known Activations