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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis or agreement in statements

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

    adding also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tembelea
    -0.48
     Signalez
    -0.45
     nakalista
    -0.38
    webElementXpaths
    -0.36
    Collegamenti
    -0.35
    delivr
    -0.35
     OnInit
    -0.33
     solchen
    -0.32
    いざ
    -0.32
    lán
    -0.32
    POSITIVE LOGITS
    今回も
    0.51
    今年も
    0.50
    ThroughAttribute
    0.47
    tissimi
    0.46
     lagi
    0.46
     ebenfalls
    0.44
    こちらも
    0.44
    scriptcase
    0.44
     too
    0.43
     тоже
    0.43
    Act Density 0.043%

    No Known Activations