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

    Neuronpedia

    INDEX
    Explanations

    references to prior experience

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

    experience with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thschild
    -0.52
    ⟬
    -0.50
     Darlington
    -0.49
     borboleta
    -0.48
    ឲ
    -0.48
    olyb
    -0.48
     direta
    -0.48
    tamol
    -0.48
    onaldo
    -0.48
     çift
    -0.47
    POSITIVE LOGITS
     experience
    1.82
     Experience
    1.68
    experience
    1.67
    Experience
    1.62
     EXPERIENCE
    1.49
     experiences
    1.47
    EXPERIENCE
    1.38
     experiencia
    1.34
     experien
    1.30
    experiences
    1.27
    Act Density 0.014%

    No Known Activations