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

    Neuronpedia

    INDEX
    Explanations

    references to incidents involving violence or struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.61
     Bewußt
    -0.47
     actualidad
    -0.45
     redacción
    -0.42
     mármol
    -0.40
     ujednoznacz
    -0.39
     dueño
    -0.39
     typelib
    -0.39
     además
    -0.38
    AutoModerator
    -0.38
    POSITIVE LOGITS
     routine
    0.56
    つも
    0.47
     Routine
    0.47
     innoc
    0.44
     unattended
    0.43
    Routine
    0.43
    weakSelf
    0.43
    WEBPACK
    0.42
    ---|---|
    0.42
     rehearsal
    0.41
    Act Density 0.484%

    No Known Activations