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

    Neuronpedia

    INDEX
    Explanations

    references to social dynamics and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emo
    -0.18
    avou
    -0.18
    urum
    -0.16
    arella
    -0.15
    اÙħÙĩ
    -0.15
    ieu
    -0.15
    imo
    -0.15
    942
    -0.14
    imler
    -0.14
     подÑģ
    -0.14
    POSITIVE LOGITS
    mgr
    0.16
     Baxter
    0.15
    /antlr
    0.14
    leaflet
    0.14
    odesk
    0.14
     Butterfly
    0.14
    iggins
    0.14
     being
    0.14
    /english
    0.13
    spath
    0.13
    Act Density 0.306%

    No Known Activations