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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals or entities, particularly those beginning with "Che."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     %>
    -0.80
    /**
    -0.78
     geb
    -0.75
     Xunit
    -0.75
     Alam
    -0.74
    gapi
    -0.74
     Velas
    -0.72
    uParam
    -0.71
    ceae
    -0.69
    getObject
    -0.69
    POSITIVE LOGITS
     Che
    2.28
    Che
    2.24
     che
    2.13
     CHE
    2.10
    che
    1.80
    CHE
    1.77
     cheating
    1.66
     cheats
    1.51
     cheat
    1.38
     Chet
    1.32
    Act Density 0.086%

    No Known Activations