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

    Neuronpedia

    INDEX
    Explanations

    abbreviations or acronyms related to various organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rules
    -0.16
    eka
    -0.16
    ered
    -0.15
    iras
    -0.15
    lw
    -0.15
    ãĥ¼ãĥ©
    -0.15
    g
    -0.15
    lg
    -0.14
    ril
    -0.14
    ippy
    -0.14
    POSITIVE LOGITS
    les
    0.17
    shaw
    0.17
    kinson
    0.16
    dale
    0.16
    hton
    0.16
    imizin
    0.16
    oth
    0.16
    iele
    0.15
    lesh
    0.15
    ren
    0.15
    Act Density 0.209%

    No Known Activations