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

    Neuronpedia

    INDEX
    Explanations

    words and phrases reflecting intelligence, understanding, and societal critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ţion
    -0.42
     navideña
    -0.40
     plazos
    -0.37
    сылкі
    -0.36
     invitado
    -0.35
    Dış
    -0.35
    afficheront
    -0.35
     drying
    -0.34
     noDo
    -0.34
    lső
    -0.34
    POSITIVE LOGITS
     stupidity
    0.84
     stupid
    0.73
     Stupid
    0.71
    stupid
    0.68
    Stupid
    0.67
     incompetence
    0.65
     imbec
    0.64
     morons
    0.63
     dumb
    0.63
     idiots
    0.62
    Act Density 0.437%

    No Known Activations