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

    Neuronpedia

    INDEX
    Explanations

    conversational language and expressions of opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .googlecode
    -0.18
     geek
    -0.17
     Zombies
    -0.16
     Prostit
    -0.16
     hookers
    -0.16
    OUCH
    -0.15
     Awesome
    -0.15
    ÏĢα
    -0.15
     Ãĥ
    -0.15
     xrange
    -0.15
    POSITIVE LOGITS
     stan
    0.28
    202
    0.24
     rn
    0.22
     tb
    0.22
     vibes
    0.21
     literal
    0.20
     covid
    0.20
     Literal
    0.20
     Tik
    0.20
     MCU
    0.19
    Act Density 0.933%

    No Known Activations