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

    Neuronpedia

    INDEX
    Explanations

    terms related to revolution and significant social change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OOT
    -0.15
    à¸ģ
    -0.15
    olan
    -0.15
    elah
    -0.14
    amon
    -0.14
    elier
    -0.14
    oga
    -0.14
    uro
    -0.14
    comings
    -0.14
    pear
    -0.13
    POSITIVE LOGITS
    aries
    0.23
    arily
    0.22
    -era
    0.18
    esimal
    0.17
    itz
    0.16
    undy
    0.16
    ized
    0.15
    -ending
    0.15
    defer
    0.14
    irement
    0.14
    Act Density 0.027%

    No Known Activations