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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations, government-related terms like agencies or programs, and incidents of national significance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doodle
    -0.73
     alloc
    -0.62
     preceding
    -0.59
     sake
    -0.57
     CITY
    -0.55
    uces
    -0.53
     Cox
    -0.53
     Jackets
    -0.53
     Blues
    -0.52
     apologies
    -0.52
    POSITIVE LOGITS
     jeopardy
    0.89
    fortable
    0.88
     danger
    0.87
    lined
    0.82
     trouble
    0.82
    active
    0.81
    itialized
    0.80
    occupied
    0.80
    oult
    0.79
    enced
    0.79
    Act Density 2.371%

    No Known Activations