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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebb
    -0.15
     Kamp
    -0.14
    ativos
    -0.14
    erval
    -0.14
     McKay
    -0.13
     MOS
    -0.13
    edom
    -0.13
    Ing
    -0.13
     Davies
    -0.13
    .localized
    -0.13
    POSITIVE LOGITS
    OKIE
    0.17
    ÙħÙĨت
    0.17
     conclusions
    0.16
    uan
    0.16
     opposite
    0.16
    mlink
    0.15
    Decision
    0.15
    uls
    0.15
    emann
    0.15
     conclusion
    0.15
    Act Density 0.045%

    No Known Activations