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

    Neuronpedia

    INDEX
    Explanations

    references to specific weeks or weekend events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uilder
    -0.17
    izar
    -0.16
    ousel
    -0.16
    izada
    -0.16
    osti
    -0.15
    okrat
    -0.15
    cheid
    -0.15
    istrat
    -0.14
    .persistent
    -0.14
    eut
    -0.14
    POSITIVE LOGITS
    ender
    0.32
    ends
    0.29
    day
    0.28
    enders
    0.27
    night
    0.27
    lyph
    0.26
    ending
    0.25
    ely
    0.25
    end
    0.25
    lys
    0.24
    Act Density 0.011%

    No Known Activations