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

    Neuronpedia

    INDEX
    Explanations

    topics related to controversial social issues and political commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     geek
    -0.17
    OUCH
    -0.17
     Zombies
    -0.16
    ÏĢα
    -0.16
    acman
    -0.15
     Prostit
    -0.15
     Zombie
    -0.15
     Zot
    -0.15
    .googlecode
    -0.15
     xrange
    -0.14
    POSITIVE LOGITS
     stan
    0.24
    202
    0.21
     rn
    0.21
     tb
    0.20
     Literal
    0.20
     vibes
    0.19
     tf
    0.19
     wholesome
    0.18
     quarantine
    0.18
     literal
    0.18
    Act Density 1.430%

    No Known Activations