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

    Neuronpedia

    INDEX
    Explanations

    references to problems and solutions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occasionally
    -0.17
    nech
    -0.17
    ulfilled
    -0.16
    ernaut
    -0.15
    ombat
    -0.15
    finally
    -0.15
     Occasionally
    -0.15
     periodically
    -0.15
     finally
    -0.15
     preceding
    -0.14
    POSITIVE LOGITS
     immediately
    0.95
     immediate
    0.85
     immedi
    0.75
     instantly
    0.74
     sofort
    0.70
     Immediately
    0.69
     Immediate
    0.65
     instant
    0.60
     quickly
    0.57
    ç«ĭåĪ»
    0.56
    Act Density 1.565%

    No Known Activations