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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal freedom and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersh
    -0.19
    WEBPACK
    -0.17
    ãģıãĤĵ
    -0.16
    arend
    -0.15
    ender
    -0.15
    gii
    -0.15
    ertas
    -0.15
    roz
    -0.14
    robe
    -0.14
    arket
    -0.14
    POSITIVE LOGITS
     themselves
    0.25
     inherit
    0.19
     voting
    0.18
     flock
    0.17
    ourcing
    0.16
     collective
    0.16
    ĥ
    0.15
    volt
    0.15
    fold
    0.15
     голоÑģ
    0.15
    Act Density 0.276%

    No Known Activations