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

    Neuronpedia

    INDEX
    Explanations

    phrases that reflect societal conditions and shifts in cultural or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raman
    -0.18
    ercial
    -0.16
    exas
    -0.14
    attern
    -0.14
    hek
    -0.14
     onUpdate
    -0.14
    luv
    -0.14
    ackbar
    -0.14
    etz
    -0.14
     Arms
    -0.14
    POSITIVE LOGITS
    å»
    0.16
    .opend
    0.15
    ato
    0.14
    -blind
    0.14
    Alle
    0.14
    uco
    0.14
    ACHI
    0.14
    åª
    0.13
    AVE
    0.13
    adden
    0.13
    Act Density 0.123%

    No Known Activations