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

    Neuronpedia

    INDEX
    Explanations

    issues related to personal responsibility and societal critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.51
    олові
    -0.50
    Datuak
    -0.46
    なかなか
    -0.44
     angusti
    -0.44
     modelAndView
    -0.43
     gynhyrchwyd
    -0.42
    LabelTagHelper
    -0.42
     morgon
    -0.42
     ostavi
    -0.42
    POSITIVE LOGITS
     morons
    0.92
     hypocritical
    0.88
     dumbass
    0.84
     idiotic
    0.83
     fucking
    0.83
     hypocrisy
    0.81
     lmfao
    0.80
     lmao
    0.80
     idiots
    0.80
     ignorant
    0.78
    Act Density 1.545%

    No Known Activations