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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing learning from experiences or mistakes

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

    lessons learned from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rela
    -0.42
     recla
    -0.40
     setDate
    -0.39
    WebControls
    -0.39
    scroller
    -0.37
    Insee
    -0.37
    يميديا
    -0.36
     poffe
    -0.36
    ellschaft
    -0.36
     explosion
    -0.36
    POSITIVE LOGITS
     leçons
    0.61
     aprendizagem
    0.60
     endwhile
    0.56
    aprend
    0.55
     învă
    0.55
     amitié
    0.55
     lära
    0.53
     aprendizaje
    0.53
     bambú
    0.52
     amizade
    0.52
    Act Density 0.010%

    No Known Activations