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

    Neuronpedia

    INDEX
    Explanations

    references to assignments in various contexts

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

    assignment or assigned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sereia
    -0.55
     vemos
    -0.54
     voces
    -0.54
     pieles
    -0.54
     Grüsse
    -0.54
     leher
    -0.50
     burbujas
    -0.50
     polícia
    -0.50
     genç
    -0.49
     perlas
    -0.49
    POSITIVE LOGITS
     assignment
    1.79
     assignments
    1.67
     Assignment
    1.63
     Assignments
    1.59
     assigned
    1.57
    Assignment
    1.49
    assignment
    1.45
     Assigned
    1.40
    assignments
    1.40
    Assignments
    1.33
    Act Density 0.009%

    No Known Activations