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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceedance or surpassing limits

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

    going above and beyond

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rptr
    -0.44
    Tembelea
    -0.43
     ivelany
    -0.42
     Meksiku
    -0.42
    thâu
    -0.42
     ligiloj
    -0.41
    .*")]
    -0.40
     Италијани
    -0.40
     Rptr
    -0.40
    thiet
    -0.40
    POSITIVE LOGITS
     Photocase
    0.59
     excellence
    0.59
     beyond
    0.58
    beyond
    0.58
     Excellence
    0.55
     BEYOND
    0.54
     Beyond
    0.53
    Excellence
    0.52
     Extraordinary
    0.52
     amazing
    0.51
    Act Density 0.001%

    No Known Activations