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

    Neuronpedia

    INDEX
    Explanations

    references to slurring, particularly in speech and other contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    slur, naltrexone, construed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.66
    UnusedPrivate
    -0.55
    github
    -0.51
     насељу
    -0.51
    MockBean
    -0.50
     SDLK
    -0.50
    IUrlHelper
    -0.50
     незавершена
    -0.50
    canActivate
    -0.50
     berger
    -0.47
    POSITIVE LOGITS
    philo
    0.81
     slur
    0.71
     baton
    0.67
     Baton
    0.65
     Nal
    0.65
    Kristina
    0.64
    Nal
    0.62
    Carlton
    0.57
     Kristina
    0.56
     Broom
    0.53
    Act Density 0.009%

    No Known Activations